Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
9d05f77a9b | ||
|
|
23e093fc75 | ||
|
|
f77ce4dff2 |
@@ -1,194 +1,757 @@
|
||||
[
|
||||
{
|
||||
"id": "screenshot_github_home",
|
||||
"id": "screenshot_github_mark",
|
||||
"url": "https://github.githubassets.com/images/modules/logos_page/GitHub-Mark.png",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": ["github", "logo", "mark"],
|
||||
"expected_keywords": [
|
||||
"github",
|
||||
"logo",
|
||||
"mark"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "diagram_mermaid_flow",
|
||||
"url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6siSZXVhjQTlgl1nigHg5fRBOzSfebopROCu_cytObSfgLSE1ANOeZWkO2IH5upZxYot8m1hqAdpD_63WRl0xdUG1jdl9kPiOb_EWk2JBtPaiKkF4eVIYgO0EtkW-RSgC4gJ6HJYRG1UNdN0HNVd0Bftjj7X8P92qPj-F8l8T3w",
|
||||
"id": "screenshot_github_social",
|
||||
"url": "https://github.githubassets.com/images/modules/site/social-cards.png",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": [
|
||||
"github",
|
||||
"page",
|
||||
"web"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "screenshot_github_code_search",
|
||||
"url": "https://github.githubassets.com/images/modules/site/features-code-search.png",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": [
|
||||
"search",
|
||||
"code",
|
||||
"feature"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "screenshot_terminal_capture",
|
||||
"url": "https://raw.githubusercontent.com/nicehash/nicehash-quick-start/main/images/nicehash-terminal.png",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": [
|
||||
"terminal",
|
||||
"command",
|
||||
"output"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "screenshot_http_404",
|
||||
"url": "https://http.cat/404.jpg",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": [
|
||||
"404",
|
||||
"error",
|
||||
"cat"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "screenshot_dummy_cli_01",
|
||||
"url": "https://dummyimage.com/1280x720/111827/f9fafb.png&text=Hermes+CLI+Session+01",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": [
|
||||
"hermes",
|
||||
"cli",
|
||||
"session"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "screenshot_dummy_cli_02",
|
||||
"url": "https://dummyimage.com/1280x720/0f172a/e2e8f0.png&text=Prompt+Cache+Dashboard",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": [
|
||||
"prompt",
|
||||
"cache",
|
||||
"dashboard"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "screenshot_dummy_ui_01",
|
||||
"url": "https://dummyimage.com/1280x720/1f2937/f3f4f6.png&text=Settings+Panel+Voice+Mode",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": [
|
||||
"settings",
|
||||
"voice",
|
||||
"mode"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "screenshot_dummy_ui_02",
|
||||
"url": "https://dummyimage.com/1280x720/334155/f8fafc.png&text=Browser+Vision+Preview",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": [
|
||||
"browser",
|
||||
"vision",
|
||||
"preview"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "screenshot_dummy_ui_03",
|
||||
"url": "https://dummyimage.com/1280x720/111827/ffffff.png&text=Tool+Call+Inspector",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": [
|
||||
"tool",
|
||||
"call",
|
||||
"inspector"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "diagram_flow_a",
|
||||
"url": "https://dummyimage.com/1200x800/f8fafc/0f172a.png&text=Flowchart+API+Gateway+Queue+Worker",
|
||||
"category": "diagram",
|
||||
"expected_keywords": ["flow", "diagram", "process"],
|
||||
"expected_keywords": [
|
||||
"flowchart",
|
||||
"api",
|
||||
"worker"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_1",
|
||||
"url": "https://picsum.photos/seed/vision1/400/300",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"id": "diagram_flow_b",
|
||||
"url": "https://dummyimage.com/1200x800/f1f5f9/0f172a.png&text=Architecture+Diagram+Database+Cache+Client",
|
||||
"category": "diagram",
|
||||
"expected_keywords": [
|
||||
"architecture",
|
||||
"diagram",
|
||||
"cache"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_2",
|
||||
"url": "https://picsum.photos/seed/vision2/400/300",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"id": "diagram_uml_a",
|
||||
"url": "https://dummyimage.com/1200x800/e2e8f0/0f172a.png&text=Class+Diagram+User+Session+Message",
|
||||
"category": "diagram",
|
||||
"expected_keywords": [
|
||||
"class",
|
||||
"diagram",
|
||||
"session"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "chart_simple_bar",
|
||||
"url": "https://quickchart.io/chart?c={type:'bar',data:{labels:['Q1','Q2','Q3','Q4'],datasets:[{label:'Revenue',data:[100,150,200,250]}]}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": ["bar", "chart", "revenue"],
|
||||
"id": "diagram_uml_b",
|
||||
"url": "https://dummyimage.com/1200x800/cbd5e1/0f172a.png&text=Sequence+Diagram+Request+Response",
|
||||
"category": "diagram",
|
||||
"expected_keywords": [
|
||||
"sequence",
|
||||
"diagram",
|
||||
"response"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "chart_pie",
|
||||
"url": "https://quickchart.io/chart?c={type:'pie',data:{labels:['A','B','C'],datasets:[{data:[30,50,20]}]}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": ["pie", "chart", "percentage"],
|
||||
"id": "diagram_network_a",
|
||||
"url": "https://dummyimage.com/1200x800/ffffff/111827.png&text=Network+Nodes+Edges+Router",
|
||||
"category": "diagram",
|
||||
"expected_keywords": [
|
||||
"network",
|
||||
"node",
|
||||
"router"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "diagram_network_b",
|
||||
"url": "https://dummyimage.com/1200x800/ffffff/1e293b.png&text=Service+Mesh+Proxy+Auth",
|
||||
"category": "diagram",
|
||||
"expected_keywords": [
|
||||
"service",
|
||||
"mesh",
|
||||
"auth"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "diagram_state_machine",
|
||||
"url": "https://dummyimage.com/1200x800/f8fafc/334155.png&text=State+Machine+Idle+Run+Stop",
|
||||
"category": "diagram",
|
||||
"expected_keywords": [
|
||||
"state",
|
||||
"machine",
|
||||
"idle"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "diagram_mind_map",
|
||||
"url": "https://dummyimage.com/1200x800/fefce8/1f2937.png&text=Mind+Map+Memory+Recall+Tools",
|
||||
"category": "diagram",
|
||||
"expected_keywords": [
|
||||
"mind",
|
||||
"memory",
|
||||
"tools"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "diagram_pipeline",
|
||||
"url": "https://dummyimage.com/1200x800/ecfeff/155e75.png&text=Pipeline+Ingest+Rank+Summarize",
|
||||
"category": "diagram",
|
||||
"expected_keywords": [
|
||||
"pipeline",
|
||||
"ingest",
|
||||
"summarize"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "diagram_org_chart",
|
||||
"url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6iuyIWyrLgXLALrPEAfFy-iCcmk-83RSjcFZ-51ac2k7AW0JqAKY9y9IcsAPzdS3jxBb5NrHUAraH_lutjbpi6oJqG7P7IPEd3-ItJsWCaO1FVYLw8qQwANsJbIt8i1AExAX0OCwjNqoa6LoPaq7oCvbHHmv5f7pVfX4K5b8mvg",
|
||||
"url": "https://dummyimage.com/1200x800/fdf2f8/831843.png&text=Org+Chart+Lead+Review+Ops",
|
||||
"category": "diagram",
|
||||
"expected_keywords": ["organization", "hierarchy", "chart"],
|
||||
"expected_keywords": [
|
||||
"org",
|
||||
"chart",
|
||||
"review"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "screenshot_terminal",
|
||||
"url": "https://raw.githubusercontent.com/nicehash/nicehash-quick-start/main/images/nicehash-terminal.png",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": ["terminal", "command", "output"],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_3",
|
||||
"url": "https://picsum.photos/seed/vision3/400/300",
|
||||
"id": "photo_random_01",
|
||||
"url": "https://picsum.photos/seed/vision-bench-1/640/480",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "chart_line",
|
||||
"id": "photo_random_02",
|
||||
"url": "https://picsum.photos/seed/vision-bench-2/640/480",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_03",
|
||||
"url": "https://picsum.photos/seed/vision-bench-3/640/480",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_04",
|
||||
"url": "https://picsum.photos/seed/vision-bench-4/640/480",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_05",
|
||||
"url": "https://picsum.photos/seed/vision-bench-5/640/480",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_06",
|
||||
"url": "https://picsum.photos/seed/vision-bench-6/640/480",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_07",
|
||||
"url": "https://picsum.photos/seed/vision-bench-7/640/480",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_08",
|
||||
"url": "https://picsum.photos/seed/vision-bench-8/640/480",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_09",
|
||||
"url": "https://picsum.photos/seed/vision-bench-9/640/480",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_10",
|
||||
"url": "https://picsum.photos/seed/vision-bench-10/640/480",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 30,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "chart_bar_quarterly",
|
||||
"url": "https://quickchart.io/chart?c={type:'bar',data:{labels:['Q1','Q2','Q3','Q4'],datasets:[{label:'Revenue',data:[100,150,200,250]}]}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": [
|
||||
"bar",
|
||||
"chart",
|
||||
"revenue"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "chart_pie_market",
|
||||
"url": "https://quickchart.io/chart?c={type:'pie',data:{labels:['A','B','C'],datasets:[{data:[30,50,20]}]}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": [
|
||||
"pie",
|
||||
"chart",
|
||||
"percentage"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "chart_line_temp",
|
||||
"url": "https://quickchart.io/chart?c={type:'line',data:{labels:['Jan','Feb','Mar','Apr'],datasets:[{label:'Temperature',data:[5,8,12,18]}]}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": ["line", "chart", "temperature"],
|
||||
"expected_keywords": [
|
||||
"line",
|
||||
"chart",
|
||||
"temperature"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "diagram_sequence",
|
||||
"url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6iuyIWyrLgXLALrPEAfFy-iCcmk-83RSjcFZ-51ac2k7AW0JqAKY9y9IcsAPzdS3jxBb5NrHUAraH_lutjbpi6oJqG7P7IPEd3-ItJsWCaO1FVYLw8qQwANsJbIt8i1AExAX0OCwjNqoa6LoPaq7oCvbHHmv5f7pVfX4K5b8mvg",
|
||||
"category": "diagram",
|
||||
"expected_keywords": ["sequence", "interaction", "message"],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_4",
|
||||
"url": "https://picsum.photos/seed/vision4/400/300",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
|
||||
},
|
||||
{
|
||||
"id": "screenshot_webpage",
|
||||
"url": "https://github.githubassets.com/images/modules/site/social-cards.png",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": ["github", "page", "web"],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
|
||||
},
|
||||
{
|
||||
"id": "chart_radar",
|
||||
"id": "chart_radar_skill",
|
||||
"url": "https://quickchart.io/chart?c={type:'radar',data:{labels:['Speed','Power','Defense','Magic'],datasets:[{label:'Hero',data:[80,60,70,90]}]}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": ["radar", "chart", "skill"],
|
||||
"expected_keywords": [
|
||||
"radar",
|
||||
"chart",
|
||||
"skill"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_5",
|
||||
"url": "https://picsum.photos/seed/vision5/400/300",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
|
||||
},
|
||||
{
|
||||
"id": "diagram_class",
|
||||
"url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6iuyIWyrLgXLALrPEAfFy-iCcmk-83RSjcFZ-51ac2k7AW0JqAKY9y9IcsAPzdS3jxBb5NrHUAraH_lutjbpi6oJqG7P7IPEd3-ItJsWCaO1FVYLw8qQwANsJbIt8i1AExAX0OCwjNqoa6LoPaq7oCvbHHmv5f7pVfX4K5b8mvg",
|
||||
"category": "diagram",
|
||||
"expected_keywords": ["class", "object", "attribute"],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
|
||||
},
|
||||
{
|
||||
"id": "chart_doughnut",
|
||||
"url": "https://quickchart.io/chart?c={type:'doughnut',data:{labels:['Desktop','Mobile','Tablet'],datasets:[{data:[60,30,10]}]}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": ["doughnut", "chart", "device"],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_6",
|
||||
"url": "https://picsum.photos/seed/vision6/400/300",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
|
||||
},
|
||||
{
|
||||
"id": "screenshot_error",
|
||||
"url": "https://http.cat/404.jpg",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": ["404", "error", "cat"],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": true}
|
||||
},
|
||||
{
|
||||
"id": "diagram_network",
|
||||
"url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6iuyIWyrLgXLALrPEAfFy-iCcmk-83RSjcFZ-51ac2k7AW0JqAKY9y9IcsAPzdS3jxBb5NrHUAraH_lutjbpi6oJqG7P7IPEd3-ItJsWCaO1FVYLw8qQwANsJbIt8i1AExAX0OCwjNqoa6LoPaq7oCvbHHmv5f7pVfX4K5b8mvg",
|
||||
"category": "diagram",
|
||||
"expected_keywords": ["network", "node", "connection"],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_7",
|
||||
"url": "https://picsum.photos/seed/vision7/400/300",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
|
||||
},
|
||||
{
|
||||
"id": "chart_stacked_bar",
|
||||
"id": "chart_stacked_cloud",
|
||||
"url": "https://quickchart.io/chart?c={type:'bar',data:{labels:['2022','2023','2024'],datasets:[{label:'Cloud',data:[100,150,200]},{label:'On-prem',data:[200,180,160]}]},options:{scales:{x:{stacked:true},y:{stacked:true}}}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": ["stacked", "bar", "chart"],
|
||||
"expected_keywords": [
|
||||
"stacked",
|
||||
"bar",
|
||||
"chart"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "screenshot_dashboard",
|
||||
"url": "https://github.githubassets.com/images/modules/site/features-code-search.png",
|
||||
"category": "screenshot",
|
||||
"expected_keywords": ["search", "code", "feature"],
|
||||
"id": "chart_area_growth",
|
||||
"url": "https://quickchart.io/chart?c={type:'line',data:{labels:['W1','W2','W3','W4'],datasets:[{label:'Growth',data:[10,15,18,24],fill:true}]}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": [
|
||||
"line",
|
||||
"growth",
|
||||
"chart"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "photo_random_8",
|
||||
"url": "https://picsum.photos/seed/vision8/400/300",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"id": "chart_scatter_eval",
|
||||
"url": "https://quickchart.io/chart?c={type:'scatter',data:{datasets:[{label:'Runs',data:[{x:1,y:70},{x:2,y:75},{x:3,y:82}]}]}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": [
|
||||
"scatter",
|
||||
"chart",
|
||||
"runs"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "chart_horizontal_bar",
|
||||
"url": "https://quickchart.io/chart?c={type:'bar',data:{labels:['UI','OCR','Docs'],datasets:[{label:'Score',data:[88,76,91]}]},options:{indexAxis:'y'}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": [
|
||||
"bar",
|
||||
"score",
|
||||
"ocr"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "chart_bubble_usage",
|
||||
"url": "https://quickchart.io/chart?c={type:'bubble',data:{datasets:[{label:'Latency',data:[{x:1,y:120,r:8},{x:2,y:95,r:6},{x:3,y:180,r:10}]}]}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": [
|
||||
"bubble",
|
||||
"latency",
|
||||
"chart"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "chart_doughnut_devices",
|
||||
"url": "https://quickchart.io/chart?c={type:'doughnut',data:{labels:['Desktop','Mobile','Tablet'],datasets:[{data:[60,30,10]}]}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": [
|
||||
"doughnut",
|
||||
"chart",
|
||||
"device"
|
||||
],
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {
|
||||
"min_length": 50,
|
||||
"min_sentences": 2,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "ocr_text_01",
|
||||
"url": "https://dummyimage.com/1200x320/ffffff/000000.png&text=Hermes+OCR+Alpha+01",
|
||||
"category": "ocr",
|
||||
"expected_keywords": [
|
||||
"hermes",
|
||||
"ocr"
|
||||
],
|
||||
"ground_truth_ocr": "Hermes OCR Alpha 01",
|
||||
"expected_structure": {
|
||||
"min_length": 10,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "ocr_text_02",
|
||||
"url": "https://dummyimage.com/1200x320/ffffff/000000.png&text=Prompt+Cache+Hit+87%",
|
||||
"category": "ocr",
|
||||
"expected_keywords": [
|
||||
"prompt",
|
||||
"cache"
|
||||
],
|
||||
"ground_truth_ocr": "Prompt Cache Hit 87%",
|
||||
"expected_structure": {
|
||||
"min_length": 10,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "ocr_text_03",
|
||||
"url": "https://dummyimage.com/1200x320/ffffff/000000.png&text=Session+42+Ready",
|
||||
"category": "ocr",
|
||||
"expected_keywords": [
|
||||
"session",
|
||||
"42"
|
||||
],
|
||||
"ground_truth_ocr": "Session 42 Ready",
|
||||
"expected_structure": {
|
||||
"min_length": 10,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "ocr_text_04",
|
||||
"url": "https://dummyimage.com/1200x320/ffffff/000000.png&text=Latency+118+ms",
|
||||
"category": "ocr",
|
||||
"expected_keywords": [
|
||||
"latency",
|
||||
"118"
|
||||
],
|
||||
"ground_truth_ocr": "Latency 118 ms",
|
||||
"expected_structure": {
|
||||
"min_length": 10,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "ocr_text_05",
|
||||
"url": "https://dummyimage.com/1200x320/ffffff/000000.png&text=Voice+Mode+Enabled",
|
||||
"category": "ocr",
|
||||
"expected_keywords": [
|
||||
"voice",
|
||||
"mode"
|
||||
],
|
||||
"ground_truth_ocr": "Voice Mode Enabled",
|
||||
"expected_structure": {
|
||||
"min_length": 10,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "document_text_01",
|
||||
"url": "https://dummyimage.com/1400x900/f8fafc/0f172a.png&text=Invoice+1001+Total+42+Due+2026-04-22",
|
||||
"category": "document",
|
||||
"expected_keywords": [
|
||||
"invoice",
|
||||
"1001",
|
||||
"total"
|
||||
],
|
||||
"ground_truth_ocr": "Invoice 1001 Total 42 Due 2026-04-22",
|
||||
"expected_structure": {
|
||||
"min_length": 20,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "document_text_02",
|
||||
"url": "https://dummyimage.com/1400x900/f8fafc/0f172a.png&text=Form+A+Name+Alice+Status+Approved",
|
||||
"category": "document",
|
||||
"expected_keywords": [
|
||||
"form",
|
||||
"a",
|
||||
"name"
|
||||
],
|
||||
"ground_truth_ocr": "Form A Name Alice Status Approved",
|
||||
"expected_structure": {
|
||||
"min_length": 20,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "document_text_03",
|
||||
"url": "https://dummyimage.com/1400x900/f8fafc/0f172a.png&text=Report+Memory+Recall+Score+91+Percent",
|
||||
"category": "document",
|
||||
"expected_keywords": [
|
||||
"report",
|
||||
"memory",
|
||||
"recall"
|
||||
],
|
||||
"ground_truth_ocr": "Report Memory Recall Score 91 Percent",
|
||||
"expected_structure": {
|
||||
"min_length": 20,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "document_text_04",
|
||||
"url": "https://dummyimage.com/1400x900/f8fafc/0f172a.png&text=Checklist+Crisis+Escalation+Call+988+Now",
|
||||
"category": "document",
|
||||
"expected_keywords": [
|
||||
"checklist",
|
||||
"crisis",
|
||||
"escalation"
|
||||
],
|
||||
"ground_truth_ocr": "Checklist Crisis Escalation Call 988 Now",
|
||||
"expected_structure": {
|
||||
"min_length": 20,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "document_text_05",
|
||||
"url": "https://dummyimage.com/1400x900/f8fafc/0f172a.png&text=Meeting+Notes+Vision+Benchmark+Run+Pending",
|
||||
"category": "document",
|
||||
"expected_keywords": [
|
||||
"meeting",
|
||||
"notes",
|
||||
"vision"
|
||||
],
|
||||
"ground_truth_ocr": "Meeting Notes Vision Benchmark Run Pending",
|
||||
"expected_structure": {
|
||||
"min_length": 20,
|
||||
"min_sentences": 1,
|
||||
"has_numbers": false
|
||||
}
|
||||
}
|
||||
]
|
||||
]
|
||||
@@ -22,10 +22,12 @@ import argparse
|
||||
import asyncio
|
||||
import base64
|
||||
import json
|
||||
import mimetypes
|
||||
import os
|
||||
import statistics
|
||||
import sys
|
||||
import time
|
||||
import urllib.request
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional
|
||||
@@ -41,12 +43,16 @@ MODELS = {
|
||||
"model_id": "google/gemma-4-27b-it",
|
||||
"display_name": "Gemma 4 27B",
|
||||
"provider": "nous",
|
||||
"fallback_provider": "ollama",
|
||||
"fallback_model_id": "gemma4:latest",
|
||||
"description": "Google's multimodal Gemma 4 model",
|
||||
},
|
||||
"gemini3_flash": {
|
||||
"model_id": "google/gemini-3-flash-preview",
|
||||
"display_name": "Gemini 3 Flash Preview",
|
||||
"provider": "openrouter",
|
||||
"fallback_provider": "gemini",
|
||||
"fallback_model_id": "gemini-2.5-flash",
|
||||
"description": "Current default vision model",
|
||||
},
|
||||
}
|
||||
@@ -84,91 +90,150 @@ async def analyze_with_model(
|
||||
"""
|
||||
import httpx
|
||||
|
||||
def _load_image_bytes_cached() -> tuple[bytes, str]:
|
||||
nonlocal _image_bytes, _mime_type
|
||||
if _image_bytes is not None:
|
||||
return _image_bytes, _mime_type
|
||||
if image_url.startswith(("http://", "https://")):
|
||||
with urllib.request.urlopen(image_url, timeout=30) as resp:
|
||||
_image_bytes = resp.read()
|
||||
_mime_type = resp.headers.get_content_type() or mimetypes.guess_type(image_url)[0] or "image/png"
|
||||
else:
|
||||
path = Path(image_url).expanduser()
|
||||
_image_bytes = path.read_bytes()
|
||||
_mime_type = mimetypes.guess_type(str(path))[0] or "image/png"
|
||||
return _image_bytes, _mime_type
|
||||
|
||||
def _data_url() -> str:
|
||||
image_bytes, mime_type = _load_image_bytes_cached()
|
||||
return f"data:{mime_type};base64,{base64.b64encode(image_bytes).decode()}"
|
||||
|
||||
def _provider_key(provider: str) -> str:
|
||||
if provider == "openrouter":
|
||||
return os.getenv("OPENROUTER_API_KEY", "")
|
||||
if provider == "nous":
|
||||
return os.getenv("NOUS_API_KEY", "") or os.getenv("NOUS_INFERENCE_API_KEY", "")
|
||||
if provider == "gemini":
|
||||
return os.getenv("GEMINI_API_KEY", "") or os.getenv("GOOGLE_API_KEY", "")
|
||||
return os.getenv(f"{provider.upper()}_API_KEY", "")
|
||||
|
||||
provider = model_config["provider"]
|
||||
model_id = model_config["model_id"]
|
||||
candidates = [(provider, model_id)]
|
||||
if model_config.get("fallback_provider") and model_config.get("fallback_model_id"):
|
||||
candidates.append((model_config["fallback_provider"], model_config["fallback_model_id"]))
|
||||
|
||||
# Prepare messages
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "text", "text": prompt},
|
||||
{"type": "image_url", "image_url": {"url": image_url}},
|
||||
],
|
||||
}
|
||||
]
|
||||
_image_bytes: Optional[bytes] = None
|
||||
_mime_type = "image/png"
|
||||
failures = []
|
||||
|
||||
# Route to provider
|
||||
if provider == "openrouter":
|
||||
api_url = "https://openrouter.ai/api/v1/chat/completions"
|
||||
api_key = os.getenv("OPENROUTER_API_KEY", "")
|
||||
elif provider == "nous":
|
||||
api_url = "https://inference.nousresearch.com/v1/chat/completions"
|
||||
api_key = os.getenv("NOUS_API_KEY", "") or os.getenv("NOUS_INFERENCE_API_KEY", "")
|
||||
else:
|
||||
api_url = os.getenv(f"{provider.upper()}_API_URL", "")
|
||||
api_key = os.getenv(f"{provider.upper()}_API_KEY", "")
|
||||
for candidate_provider, candidate_model in candidates:
|
||||
api_key = _provider_key(candidate_provider)
|
||||
start = time.perf_counter()
|
||||
try:
|
||||
if candidate_provider in {"openrouter", "nous"}:
|
||||
api_url = (
|
||||
"https://openrouter.ai/api/v1/chat/completions"
|
||||
if candidate_provider == "openrouter"
|
||||
else "https://inference.nousresearch.com/v1/chat/completions"
|
||||
)
|
||||
if not api_key:
|
||||
raise RuntimeError(f"No API key for provider {candidate_provider}")
|
||||
payload = {
|
||||
"model": candidate_model,
|
||||
"messages": [{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "text", "text": prompt},
|
||||
{"type": "image_url", "image_url": {"url": _data_url() if not image_url.startswith(("http://", "https://")) else image_url}},
|
||||
],
|
||||
}],
|
||||
"max_tokens": 2000,
|
||||
"temperature": 0.1,
|
||||
}
|
||||
headers = {
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"Content-Type": "application/json",
|
||||
}
|
||||
async with httpx.AsyncClient(timeout=timeout) as client:
|
||||
resp = await client.post(api_url, json=payload, headers=headers)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
analysis = data.get("choices", [{}])[0].get("message", {}).get("content", "")
|
||||
usage = data.get("usage", {})
|
||||
tokens = {
|
||||
"prompt_tokens": usage.get("prompt_tokens", 0),
|
||||
"completion_tokens": usage.get("completion_tokens", 0),
|
||||
"total_tokens": usage.get("total_tokens", 0),
|
||||
}
|
||||
elif candidate_provider == "gemini":
|
||||
if not api_key:
|
||||
raise RuntimeError("No API key for provider gemini")
|
||||
image_bytes, mime_type = _load_image_bytes_cached()
|
||||
api_url = f"https://generativelanguage.googleapis.com/v1beta/models/{candidate_model}:generateContent?key={api_key}"
|
||||
payload = {
|
||||
"contents": [{"parts": [
|
||||
{"text": prompt},
|
||||
{"inline_data": {"mime_type": mime_type, "data": base64.b64encode(image_bytes).decode()}},
|
||||
]}],
|
||||
"generationConfig": {"temperature": 0.1, "maxOutputTokens": 2000},
|
||||
}
|
||||
async with httpx.AsyncClient(timeout=timeout) as client:
|
||||
resp = await client.post(api_url, json=payload)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
parts = data.get("candidates", [{}])[0].get("content", {}).get("parts", [])
|
||||
analysis = "\n".join(part.get("text", "") for part in parts if isinstance(part, dict) and part.get("text"))
|
||||
usage = data.get("usageMetadata", {})
|
||||
tokens = {
|
||||
"prompt_tokens": usage.get("promptTokenCount", 0),
|
||||
"completion_tokens": usage.get("candidatesTokenCount", 0),
|
||||
"total_tokens": usage.get("totalTokenCount", 0),
|
||||
}
|
||||
elif candidate_provider == "ollama":
|
||||
image_bytes, _ = _load_image_bytes_cached()
|
||||
payload = {
|
||||
"model": candidate_model,
|
||||
"stream": False,
|
||||
"messages": [{"role": "user", "content": prompt, "images": [base64.b64encode(image_bytes).decode()]}],
|
||||
"options": {"temperature": 0.1},
|
||||
}
|
||||
async with httpx.AsyncClient(timeout=timeout) as client:
|
||||
resp = await client.post("http://localhost:11434/api/chat", json=payload)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
analysis = data.get("message", {}).get("content", "")
|
||||
tokens = {
|
||||
"prompt_tokens": data.get("prompt_eval_count", 0),
|
||||
"completion_tokens": data.get("eval_count", 0),
|
||||
"total_tokens": (data.get("prompt_eval_count", 0) or 0) + (data.get("eval_count", 0) or 0),
|
||||
}
|
||||
else:
|
||||
raise RuntimeError(f"Unsupported provider {candidate_provider}")
|
||||
|
||||
if not api_key:
|
||||
return {
|
||||
"analysis": "",
|
||||
"latency_ms": 0,
|
||||
"tokens": {},
|
||||
"success": False,
|
||||
"error": f"No API key for provider {provider}",
|
||||
}
|
||||
latency_ms = (time.perf_counter() - start) * 1000
|
||||
return {
|
||||
"analysis": analysis,
|
||||
"latency_ms": round(latency_ms, 1),
|
||||
"tokens": tokens,
|
||||
"success": True,
|
||||
"error": "",
|
||||
"provider_used": candidate_provider,
|
||||
"model_used": candidate_model,
|
||||
}
|
||||
except Exception as e:
|
||||
failures.append(f"{candidate_provider}:{candidate_model} => {e}")
|
||||
|
||||
headers = {
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"Content-Type": "application/json",
|
||||
return {
|
||||
"analysis": "",
|
||||
"latency_ms": 0,
|
||||
"tokens": {},
|
||||
"success": False,
|
||||
"error": " | ".join(failures) if failures else "No runs",
|
||||
"provider_used": candidates[-1][0] if candidates else provider,
|
||||
"model_used": candidates[-1][1] if candidates else model_id,
|
||||
}
|
||||
|
||||
payload = {
|
||||
"model": model_id,
|
||||
"messages": messages,
|
||||
"max_tokens": 2000,
|
||||
"temperature": 0.1,
|
||||
}
|
||||
|
||||
start = time.perf_counter()
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=timeout) as client:
|
||||
resp = await client.post(api_url, json=payload, headers=headers)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
|
||||
latency_ms = (time.perf_counter() - start) * 1000
|
||||
|
||||
analysis = ""
|
||||
choices = data.get("choices", [])
|
||||
if choices:
|
||||
msg = choices[0].get("message", {})
|
||||
analysis = msg.get("content", "")
|
||||
|
||||
usage = data.get("usage", {})
|
||||
tokens = {
|
||||
"prompt_tokens": usage.get("prompt_tokens", 0),
|
||||
"completion_tokens": usage.get("completion_tokens", 0),
|
||||
"total_tokens": usage.get("total_tokens", 0),
|
||||
}
|
||||
|
||||
return {
|
||||
"analysis": analysis,
|
||||
"latency_ms": round(latency_ms, 1),
|
||||
"tokens": tokens,
|
||||
"success": True,
|
||||
"error": "",
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
return {
|
||||
"analysis": "",
|
||||
"latency_ms": round((time.perf_counter() - start) * 1000, 1),
|
||||
"tokens": {},
|
||||
"success": False,
|
||||
"error": str(e),
|
||||
}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Evaluation metrics
|
||||
@@ -398,7 +463,13 @@ def aggregate_results(results: List[dict], models: dict) -> dict:
|
||||
failed = [r[model_name] for r in results if not r[model_name]["success"]]
|
||||
|
||||
if not model_results:
|
||||
summary[model_name] = {"success_rate": 0, "error": "All runs failed"}
|
||||
summary[model_name] = {
|
||||
"success_rate": 0,
|
||||
"error": "All runs failed",
|
||||
"total_runs": 0,
|
||||
"total_failures": len(failed),
|
||||
"failure_examples": sorted({f.get("error", "unknown failure") for f in failed})[:3],
|
||||
}
|
||||
continue
|
||||
|
||||
latencies = [r["avg_latency_ms"] for r in model_results]
|
||||
@@ -410,6 +481,7 @@ def aggregate_results(results: List[dict], models: dict) -> dict:
|
||||
"success_rate": round(len(model_results) / (len(model_results) + len(failed)), 4),
|
||||
"total_runs": len(model_results),
|
||||
"total_failures": len(failed),
|
||||
"failure_examples": sorted({f.get("error", "unknown failure") for f in failed})[:3],
|
||||
"latency": {
|
||||
"mean_ms": round(statistics.mean(latencies), 1),
|
||||
"median_ms": round(statistics.median(latencies), 1),
|
||||
@@ -495,6 +567,23 @@ def to_markdown(report: dict) -> str:
|
||||
f"| {mname} | {tok['mean_total']:.0f} | {tok['total_used']} |"
|
||||
)
|
||||
|
||||
lines += ["", "## Failure Modes", ""]
|
||||
had_failures = False
|
||||
for mkey, mname in config["models"].items():
|
||||
model_summary = summary.get(mkey, {})
|
||||
failure_examples = model_summary.get("failure_examples", [])
|
||||
if not failure_examples and not model_summary.get("error"):
|
||||
continue
|
||||
had_failures = True
|
||||
lines.append(f"### {mname}")
|
||||
if model_summary.get("error"):
|
||||
lines.append(f"- Summary: {model_summary['error']}")
|
||||
for err in failure_examples:
|
||||
lines.append(f"- {err}")
|
||||
lines.append("")
|
||||
if not had_failures:
|
||||
lines.append("- No provider/runtime failures recorded.")
|
||||
|
||||
# Verdict
|
||||
lines += ["", "## Verdict", ""]
|
||||
|
||||
@@ -516,8 +605,12 @@ def to_markdown(report: dict) -> str:
|
||||
|
||||
if best_model:
|
||||
lines.append(f"**Best overall: {best_model}** (composite score: {best_score:.1%})")
|
||||
lines.append("")
|
||||
lines.append("Recommendation: keep the best-performing Gemma/Gemini lane from this run and only switch if repeated runs disagree.")
|
||||
else:
|
||||
lines.append("No clear winner — insufficient data.")
|
||||
lines.append("Benchmark blocked or insufficient data for a trustworthy winner.")
|
||||
lines.append("")
|
||||
lines.append("Recommendation: repair provider/runtime availability, rerun the benchmark, and keep the current implementation unchanged until comparative results exist.")
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
@@ -528,44 +621,124 @@ def to_markdown(report: dict) -> str:
|
||||
|
||||
|
||||
def generate_sample_dataset() -> List[dict]:
|
||||
"""Generate a sample test dataset with diverse public images.
|
||||
"""Generate a larger benchmark dataset aligned with issue #817.
|
||||
|
||||
Returns list of test image definitions.
|
||||
Returns 50+ images across screenshots, diagrams, photos, OCR, charts,
|
||||
and document-like images so the harness matches the issue contract.
|
||||
"""
|
||||
return [
|
||||
# Screenshots
|
||||
{
|
||||
"id": "screenshot_github",
|
||||
"url": "https://github.githubassets.com/images/modules/logos_page/GitHub-Mark.png",
|
||||
dataset: List[dict] = []
|
||||
|
||||
screenshots = [
|
||||
("github_mark", "https://github.githubassets.com/images/modules/logos_page/GitHub-Mark.png", ["github", "logo", "mark"]),
|
||||
("github_social", "https://github.githubassets.com/images/modules/site/social-cards.png", ["github", "page", "web"]),
|
||||
("github_code_search", "https://github.githubassets.com/images/modules/site/features-code-search.png", ["search", "code", "feature"]),
|
||||
("terminal_capture", "https://raw.githubusercontent.com/nicehash/nicehash-quick-start/main/images/nicehash-terminal.png", ["terminal", "command", "output"]),
|
||||
("http_404", "https://http.cat/404.jpg", ["404", "error", "cat"]),
|
||||
("dummy_cli_01", "https://dummyimage.com/1280x720/111827/f9fafb.png&text=Hermes+CLI+Session+01", ["hermes", "cli", "session"]),
|
||||
("dummy_cli_02", "https://dummyimage.com/1280x720/0f172a/e2e8f0.png&text=Prompt+Cache+Dashboard", ["prompt", "cache", "dashboard"]),
|
||||
("dummy_ui_01", "https://dummyimage.com/1280x720/1f2937/f3f4f6.png&text=Settings+Panel+Voice+Mode", ["settings", "voice", "mode"]),
|
||||
("dummy_ui_02", "https://dummyimage.com/1280x720/334155/f8fafc.png&text=Browser+Vision+Preview", ["browser", "vision", "preview"]),
|
||||
("dummy_ui_03", "https://dummyimage.com/1280x720/111827/ffffff.png&text=Tool+Call+Inspector", ["tool", "call", "inspector"]),
|
||||
]
|
||||
for ident, url, keywords in screenshots:
|
||||
dataset.append({
|
||||
"id": f"screenshot_{ident}",
|
||||
"url": url,
|
||||
"category": "screenshot",
|
||||
"expected_keywords": ["github", "logo", "octocat"],
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2},
|
||||
},
|
||||
# Diagrams
|
||||
{
|
||||
"id": "diagram_architecture",
|
||||
"url": "https://mermaid.ink/img/pako:eNp9kMtOwzAQRX_F8hKpJbhJFVJBi1QJiMWCG8eZNsGJLdlOiqIid5RdufiHnZRA7GbuzJwZe4ZGH2SCBPYUwgxoQKvJnCR2YY0F5YBdJJkD4uX0oXB6PnF3U4zCWcWdW3FqOwGvCKkBmHKSTB2gJeRrLTeJLfJdJKkBGYf9P1sTNdUXVJqY3YNJK7xLVwR0mxJFU6rCgEKnhSGIL2Eq8BdEERAX0OGwEiVQ1R0MaNFR8QfqKxmHigbX8VLjDz_Q0L8Wc_qPxDw",
|
||||
"expected_keywords": keywords,
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": False},
|
||||
})
|
||||
|
||||
diagrams = [
|
||||
("flow_a", "https://dummyimage.com/1200x800/f8fafc/0f172a.png&text=Flowchart+API+Gateway+Queue+Worker", ["flowchart", "api", "worker"]),
|
||||
("flow_b", "https://dummyimage.com/1200x800/f1f5f9/0f172a.png&text=Architecture+Diagram+Database+Cache+Client", ["architecture", "diagram", "cache"]),
|
||||
("uml_a", "https://dummyimage.com/1200x800/e2e8f0/0f172a.png&text=Class+Diagram+User+Session+Message", ["class", "diagram", "session"]),
|
||||
("uml_b", "https://dummyimage.com/1200x800/cbd5e1/0f172a.png&text=Sequence+Diagram+Request+Response", ["sequence", "diagram", "response"]),
|
||||
("network_a", "https://dummyimage.com/1200x800/ffffff/111827.png&text=Network+Nodes+Edges+Router", ["network", "node", "router"]),
|
||||
("network_b", "https://dummyimage.com/1200x800/ffffff/1e293b.png&text=Service+Mesh+Proxy+Auth", ["service", "mesh", "auth"]),
|
||||
("state_machine", "https://dummyimage.com/1200x800/f8fafc/334155.png&text=State+Machine+Idle+Run+Stop", ["state", "machine", "idle"]),
|
||||
("mind_map", "https://dummyimage.com/1200x800/fefce8/1f2937.png&text=Mind+Map+Memory+Recall+Tools", ["mind", "memory", "tools"]),
|
||||
("pipeline", "https://dummyimage.com/1200x800/ecfeff/155e75.png&text=Pipeline+Ingest+Rank+Summarize", ["pipeline", "ingest", "summarize"]),
|
||||
("org_chart", "https://dummyimage.com/1200x800/fdf2f8/831843.png&text=Org+Chart+Lead+Review+Ops", ["org", "chart", "review"]),
|
||||
]
|
||||
for ident, url, keywords in diagrams:
|
||||
dataset.append({
|
||||
"id": f"diagram_{ident}",
|
||||
"url": url,
|
||||
"category": "diagram",
|
||||
"expected_keywords": ["architecture", "component", "service"],
|
||||
"expected_structure": {"min_length": 100, "min_sentences": 3},
|
||||
},
|
||||
# Photos
|
||||
{
|
||||
"id": "photo_nature",
|
||||
"url": "https://picsum.photos/seed/bench1/400/300",
|
||||
"expected_keywords": keywords,
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": False},
|
||||
})
|
||||
|
||||
for idx in range(1, 11):
|
||||
dataset.append({
|
||||
"id": f"photo_random_{idx:02d}",
|
||||
"url": f"https://picsum.photos/seed/vision-bench-{idx}/640/480",
|
||||
"category": "photo",
|
||||
"expected_keywords": [],
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1},
|
||||
},
|
||||
# Charts
|
||||
{
|
||||
"id": "chart_bar",
|
||||
"url": "https://quickchart.io/chart?c={type:'bar',data:{labels:['Q1','Q2','Q3','Q4'],datasets:[{label:'Users',data:[50,60,70,80]}]}}",
|
||||
"category": "chart",
|
||||
"expected_keywords": ["bar", "chart", "data"],
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2},
|
||||
},
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": False},
|
||||
})
|
||||
|
||||
charts = [
|
||||
("bar_quarterly", "https://quickchart.io/chart?c={type:'bar',data:{labels:['Q1','Q2','Q3','Q4'],datasets:[{label:'Revenue',data:[100,150,200,250]}]}}", ["bar", "chart", "revenue"]),
|
||||
("pie_market", "https://quickchart.io/chart?c={type:'pie',data:{labels:['A','B','C'],datasets:[{data:[30,50,20]}]}}", ["pie", "chart", "percentage"]),
|
||||
("line_temp", "https://quickchart.io/chart?c={type:'line',data:{labels:['Jan','Feb','Mar','Apr'],datasets:[{label:'Temperature',data:[5,8,12,18]}]}}", ["line", "chart", "temperature"]),
|
||||
("radar_skill", "https://quickchart.io/chart?c={type:'radar',data:{labels:['Speed','Power','Defense','Magic'],datasets:[{label:'Hero',data:[80,60,70,90]}]}}", ["radar", "chart", "skill"]),
|
||||
("stacked_cloud", "https://quickchart.io/chart?c={type:'bar',data:{labels:['2022','2023','2024'],datasets:[{label:'Cloud',data:[100,150,200]},{label:'On-prem',data:[200,180,160]}]},options:{scales:{x:{stacked:true},y:{stacked:true}}}}", ["stacked", "bar", "chart"]),
|
||||
("area_growth", "https://quickchart.io/chart?c={type:'line',data:{labels:['W1','W2','W3','W4'],datasets:[{label:'Growth',data:[10,15,18,24],fill:true}]}}", ["line", "growth", "chart"]),
|
||||
("scatter_eval", "https://quickchart.io/chart?c={type:'scatter',data:{datasets:[{label:'Runs',data:[{x:1,y:70},{x:2,y:75},{x:3,y:82}]}]}}", ["scatter", "chart", "runs"]),
|
||||
("horizontal_bar", "https://quickchart.io/chart?c={type:'bar',data:{labels:['UI','OCR','Docs'],datasets:[{label:'Score',data:[88,76,91]}]},options:{indexAxis:'y'}}", ["bar", "score", "ocr"]),
|
||||
("bubble_usage", "https://quickchart.io/chart?c={type:'bubble',data:{datasets:[{label:'Latency',data:[{x:1,y:120,r:8},{x:2,y:95,r:6},{x:3,y:180,r:10}]}]}}", ["bubble", "latency", "chart"]),
|
||||
("doughnut_devices", "https://quickchart.io/chart?c={type:'doughnut',data:{labels:['Desktop','Mobile','Tablet'],datasets:[{data:[60,30,10]}]}}", ["doughnut", "chart", "device"]),
|
||||
]
|
||||
for ident, url, keywords in charts:
|
||||
dataset.append({
|
||||
"id": f"chart_{ident}",
|
||||
"url": url,
|
||||
"category": "chart",
|
||||
"expected_keywords": keywords,
|
||||
"ground_truth_ocr": "",
|
||||
"expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": True},
|
||||
})
|
||||
|
||||
ocr_texts = [
|
||||
"Hermes OCR Alpha 01",
|
||||
"Prompt Cache Hit 87%",
|
||||
"Session 42 Ready",
|
||||
"Latency 118 ms",
|
||||
"Voice Mode Enabled",
|
||||
]
|
||||
for idx, text in enumerate(ocr_texts, start=1):
|
||||
dataset.append({
|
||||
"id": f"ocr_text_{idx:02d}",
|
||||
"url": f"https://dummyimage.com/1200x320/ffffff/000000.png&text={text.replace(' ', '+')}",
|
||||
"category": "ocr",
|
||||
"expected_keywords": text.lower().split()[:2],
|
||||
"ground_truth_ocr": text,
|
||||
"expected_structure": {"min_length": 10, "min_sentences": 1, "has_numbers": any(ch.isdigit() for ch in text)},
|
||||
})
|
||||
|
||||
documents = [
|
||||
"Invoice 1001 Total 42 Due 2026-04-22",
|
||||
"Form A Name Alice Status Approved",
|
||||
"Report Memory Recall Score 91 Percent",
|
||||
"Checklist Crisis Escalation Call 988 Now",
|
||||
"Meeting Notes Vision Benchmark Run Pending",
|
||||
]
|
||||
for idx, text in enumerate(documents, start=1):
|
||||
dataset.append({
|
||||
"id": f"document_text_{idx:02d}",
|
||||
"url": f"https://dummyimage.com/1400x900/f8fafc/0f172a.png&text={text.replace(' ', '+')}",
|
||||
"category": "document",
|
||||
"expected_keywords": text.lower().split()[:3],
|
||||
"ground_truth_ocr": text,
|
||||
"expected_structure": {"min_length": 20, "min_sentences": 1, "has_numbers": any(ch.isdigit() for ch in text)},
|
||||
})
|
||||
|
||||
return dataset
|
||||
|
||||
|
||||
def load_dataset(path: str) -> List[dict]:
|
||||
@@ -585,7 +758,9 @@ async def main():
|
||||
parser.add_argument("--url", help="Single image URL to test")
|
||||
parser.add_argument("--category", default="photo", help="Category for single URL")
|
||||
parser.add_argument("--output", default=None, help="Output JSON file")
|
||||
parser.add_argument("--markdown-output", default=None, help="Optional markdown report output path")
|
||||
parser.add_argument("--runs", type=int, default=1, help="Runs per model per image")
|
||||
parser.add_argument("--limit", type=int, default=0, help="Limit to the first N images for smoke runs")
|
||||
parser.add_argument("--models", nargs="+", default=None,
|
||||
help="Models to test (default: all)")
|
||||
parser.add_argument("--markdown", action="store_true", help="Output markdown report")
|
||||
@@ -617,9 +792,14 @@ async def main():
|
||||
print("ERROR: Provide --images or --url")
|
||||
sys.exit(1)
|
||||
|
||||
if args.limit and args.limit > 0:
|
||||
images = images[:args.limit]
|
||||
|
||||
# Run benchmark
|
||||
report = await run_benchmark_suite(images, selected, args.runs)
|
||||
|
||||
markdown_report = to_markdown(report)
|
||||
|
||||
# Output
|
||||
if args.output:
|
||||
os.makedirs(os.path.dirname(args.output) or ".", exist_ok=True)
|
||||
@@ -627,8 +807,14 @@ async def main():
|
||||
json.dump(report, f, indent=2)
|
||||
print(f"\nResults saved to {args.output}")
|
||||
|
||||
if args.markdown_output:
|
||||
os.makedirs(os.path.dirname(args.markdown_output) or ".", exist_ok=True)
|
||||
with open(args.markdown_output, "w", encoding="utf-8") as f:
|
||||
f.write(markdown_report)
|
||||
print(f"Markdown report saved to {args.markdown_output}")
|
||||
|
||||
if args.markdown or not args.output:
|
||||
print("\n" + to_markdown(report))
|
||||
print("\n" + markdown_report)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,217 +0,0 @@
|
||||
# TensorZero Evaluation Packet
|
||||
|
||||
Issue #860: [tensorzero LLMOps platform evaluation](https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/860)
|
||||
|
||||
## Scope
|
||||
|
||||
This packet evaluates TensorZero as a possible replacement for Hermes' custom provider-routing stack.
|
||||
It is intentionally grounded in the current repo state rather than a speculative cutover plan.
|
||||
|
||||
## Issue requirements being evaluated
|
||||
|
||||
- Deploy tensorzero gateway (Rust binary)
|
||||
- Migrate provider routing config
|
||||
- Test with canary (10% traffic) before full cutover
|
||||
- Feed session data for prompt optimization
|
||||
- Evaluation suite for A/B testing models
|
||||
|
||||
## Recommendation
|
||||
|
||||
Not ready for direct replacement. Recommend a shadow-evaluation phase first: keep Hermes routing live, inventory the migration seams, export SessionDB/trajectory data into an offline TensorZero experiment loop, and only design a canary gateway once percentage-based rollout controls exist.
|
||||
|
||||
## Requirement matrix
|
||||
|
||||
| Requirement | Status | Evidence labels | Summary |
|
||||
| --- | --- | --- | --- |
|
||||
| Gateway replacement scope | partial | fallback_chain, runtime_provider, gateway_provider_routing, cron_runtime_provider, auxiliary_fallback_chain, delegate_runtime_provider | Hermes already spreads provider routing across core agent, runtime provider, gateway, cron, auxiliary, and delegation seams; TensorZero would need parity across all of them before it can replace the gateway layer. |
|
||||
| Config migration | partial | provider_routing_config, runtime_provider, smart_model_routing, fallback_chain | Hermes has multiple config concepts to migrate (`provider_routing`, `fallback_providers`, `smart_model_routing`, runtime provider resolution), so TensorZero is not a drop-in config swap. |
|
||||
| 10% traffic canary | gap | — | The repo shows semantic routing and fallback, but no grounded 10% traffic-split canary mechanism. A TensorZero cutover would need new percentage-based rollout controls and observability hooks. |
|
||||
| Session data for prompt optimization | partial | session_db, trajectory_export | Hermes already has SessionDB and trajectory export surfaces that can feed offline optimization data, but not a TensorZero-native ingestion path yet. |
|
||||
| Evaluation suite / A/B testing | partial | benchmark_suite, trajectory_export | Hermes already has benchmark/trajectory machinery that can seed TensorZero A/B evaluation, but no integrated TensorZero experiment runner or live evaluation gateway. |
|
||||
|
||||
## Grounded Hermes touchpoints
|
||||
|
||||
- `run_agent.py:601` — [fallback_chain] fallback_model: Dict[str, Any] = None,
|
||||
- `run_agent.py:995` — [fallback_chain] # failure). Supports both legacy single-dict ``fallback_model`` and
|
||||
- `run_agent.py:996` — [fallback_chain] # new list ``fallback_providers`` format.
|
||||
- `run_agent.py:997` — [fallback_chain] if isinstance(fallback_model, list):
|
||||
- `run_agent.py:998` — [fallback_chain] self._fallback_chain = [
|
||||
- `run_agent.py:999` — [fallback_chain] f for f in fallback_model
|
||||
- `run_agent.py:1002` — [fallback_chain] elif isinstance(fallback_model, dict) and fallback_model.get("provider") and fallback_model.get("model"):
|
||||
- `run_agent.py:1003` — [fallback_chain] self._fallback_chain = [fallback_model]
|
||||
- `run_agent.py:1005` — [fallback_chain] self._fallback_chain = []
|
||||
- `run_agent.py:1009` — [fallback_chain] self._fallback_model = self._fallback_chain[0] if self._fallback_chain else None
|
||||
- `run_agent.py:1010` — [fallback_chain] if self._fallback_chain and not self.quiet_mode:
|
||||
- `run_agent.py:1011` — [fallback_chain] if len(self._fallback_chain) == 1:
|
||||
- `run_agent.py:1012` — [fallback_chain] fb = self._fallback_chain[0]
|
||||
- `run_agent.py:1015` — [fallback_chain] print(f"🔄 Fallback chain ({len(self._fallback_chain)} providers): " +
|
||||
- `run_agent.py:1016` — [fallback_chain] " → ".join(f"{f['model']} ({f['provider']})" for f in self._fallback_chain))
|
||||
- `run_agent.py:5624` — [fallback_chain] if self._fallback_index >= len(self._fallback_chain):
|
||||
- `run_agent.py:5627` — [fallback_chain] fb = self._fallback_chain[self._fallback_index]
|
||||
- `run_agent.py:8559` — [fallback_chain] if self._fallback_index < len(self._fallback_chain):
|
||||
- `run_agent.py:9355` — [fallback_chain] if is_rate_limited and self._fallback_index < len(self._fallback_chain):
|
||||
- `run_agent.py:10460` — [fallback_chain] if _truly_empty and self._fallback_chain:
|
||||
- `run_agent.py:10514` — [fallback_chain] + (" and fallback attempts." if self._fallback_chain else
|
||||
- `cli.py:241` — [provider_routing_config] "smart_model_routing": {
|
||||
- `cli.py:370` — [provider_routing_config] # (e.g. platform_toolsets, provider_routing, memory, honcho, etc.)
|
||||
- `cli.py:1753` — [provider_routing_config] pr = CLI_CONFIG.get("provider_routing", {}) or {}
|
||||
- `cli.py:1762` — [provider_routing_config] # Supports new list format (fallback_providers) and legacy single-dict (fallback_model).
|
||||
- `cli.py:1763` — [provider_routing_config] fb = CLI_CONFIG.get("fallback_providers") or CLI_CONFIG.get("fallback_model") or []
|
||||
- `cli.py:1770` — [provider_routing_config] self._smart_model_routing = CLI_CONFIG.get("smart_model_routing", {}) or {}
|
||||
- `cli.py:2771` — [provider_routing_config] from agent.smart_model_routing import resolve_turn_route
|
||||
- `cli.py:2776` — [provider_routing_config] self._smart_model_routing,
|
||||
- `hermes_cli/runtime_provider.py:209` — [runtime_provider] def resolve_requested_provider(requested: Optional[str] = None) -> str:
|
||||
- `hermes_cli/runtime_provider.py:649` — [runtime_provider] def resolve_runtime_provider(
|
||||
- `agent/smart_model_routing.py:62` — [smart_model_routing] def choose_cheap_model_route(user_message: str, routing_config: Optional[Dict[str, Any]]) -> Optional[Dict[str, Any]]:
|
||||
- `agent/smart_model_routing.py:110` — [smart_model_routing] def resolve_turn_route(user_message: str, routing_config: Optional[Dict[str, Any]], primary: Dict[str, Any]) -> Dict[str, Any]:
|
||||
- `gateway/run.py:1271` — [gateway_provider_routing] def _load_provider_routing() -> dict:
|
||||
- `gateway/run.py:1285` — [gateway_provider_routing] def _load_fallback_model() -> list | dict | None:
|
||||
- `gateway/run.py:1306` — [gateway_provider_routing] def _load_smart_model_routing() -> dict:
|
||||
- `cron/scheduler.py:684` — [cron_runtime_provider] pr = _cfg.get("provider_routing", {})
|
||||
- `cron/scheduler.py:688` — [cron_runtime_provider] resolve_runtime_provider,
|
||||
- `cron/scheduler.py:697` — [cron_runtime_provider] runtime = resolve_runtime_provider(**runtime_kwargs)
|
||||
- `cron/scheduler.py:702` — [cron_runtime_provider] from agent.smart_model_routing import resolve_turn_route
|
||||
- `cron/scheduler.py:703` — [cron_runtime_provider] turn_route = resolve_turn_route(
|
||||
- `cron/scheduler.py:717` — [cron_runtime_provider] fallback_model = _cfg.get("fallback_providers") or _cfg.get("fallback_model") or None
|
||||
- `cron/scheduler.py:746` — [cron_runtime_provider] fallback_model=fallback_model,
|
||||
- `agent/auxiliary_client.py:1018` — [auxiliary_fallback_chain] def _get_provider_chain() -> List[tuple]:
|
||||
- `agent/auxiliary_client.py:1107` — [auxiliary_fallback_chain] for label, try_fn in _get_provider_chain():
|
||||
- `agent/auxiliary_client.py:1189` — [auxiliary_fallback_chain] # ── Step 2: aggregator / fallback chain ──────────────────────────────
|
||||
- `agent/auxiliary_client.py:1191` — [auxiliary_fallback_chain] for label, try_fn in _get_provider_chain():
|
||||
- `agent/auxiliary_client.py:2397` — [auxiliary_fallback_chain] # error, fall through to the fallback chain below.
|
||||
- `agent/auxiliary_client.py:2417` — [auxiliary_fallback_chain] # auto (the default) = best-effort fallback chain. (#7559)
|
||||
- `agent/auxiliary_client.py:2589` — [auxiliary_fallback_chain] # error, fall through to the fallback chain below.
|
||||
- `tools/delegate_tool.py:662` — [delegate_runtime_provider] # bundle (base_url, api_key, api_mode) via the same runtime provider system
|
||||
- `tools/delegate_tool.py:854` — [delegate_runtime_provider] provider) is resolved via the runtime provider system — the same path used
|
||||
- `tools/delegate_tool.py:909` — [delegate_runtime_provider] from hermes_cli.runtime_provider import resolve_runtime_provider
|
||||
- `tools/delegate_tool.py:910` — [delegate_runtime_provider] runtime = resolve_runtime_provider(requested=configured_provider)
|
||||
- `hermes_state.py:115` — [session_db] class SessionDB:
|
||||
- `batch_runner.py:320` — [trajectory_export] save_trajectories=False, # We handle saving ourselves
|
||||
- `batch_runner.py:346` — [trajectory_export] trajectory = agent._convert_to_trajectory_format(
|
||||
- `batch_runner.py:460` — [trajectory_export] trajectory_entry = {
|
||||
- `batch_runner.py:474` — [trajectory_export] f.write(json.dumps(trajectory_entry, ensure_ascii=False) + "\n")
|
||||
- `benchmarks/tool_call_benchmark.py:3` — [benchmark_suite] Tool-Calling Benchmark — Gemma 4 vs mimo-v2-pro regression test.
|
||||
- `benchmarks/tool_call_benchmark.py:9` — [benchmark_suite] python3 benchmarks/tool_call_benchmark.py # full 100-call suite
|
||||
- `benchmarks/tool_call_benchmark.py:10` — [benchmark_suite] python3 benchmarks/tool_call_benchmark.py --limit 10 # quick smoke test
|
||||
- `benchmarks/tool_call_benchmark.py:11` — [benchmark_suite] python3 benchmarks/tool_call_benchmark.py --models nous # single model
|
||||
- `benchmarks/tool_call_benchmark.py:12` — [benchmark_suite] python3 benchmarks/tool_call_benchmark.py --category file # single category
|
||||
- `benchmarks/tool_call_benchmark.py:37` — [benchmark_suite] class ToolCall:
|
||||
- `benchmarks/tool_call_benchmark.py:51` — [benchmark_suite] ToolCall("file-01", "file", "Read the file /tmp/test_bench.txt and show me its contents.",
|
||||
- `benchmarks/tool_call_benchmark.py:53` — [benchmark_suite] ToolCall("file-02", "file", "Write 'hello benchmark' to /tmp/test_bench_out.txt",
|
||||
- `benchmarks/tool_call_benchmark.py:55` — [benchmark_suite] ToolCall("file-03", "file", "Search for the word 'import' in all Python files in the current directory.",
|
||||
- `benchmarks/tool_call_benchmark.py:57` — [benchmark_suite] ToolCall("file-04", "file", "Read lines 1-20 of /etc/hosts",
|
||||
- `benchmarks/tool_call_benchmark.py:59` — [benchmark_suite] ToolCall("file-05", "file", "Patch /tmp/test_bench_out.txt: replace 'hello' with 'goodbye'",
|
||||
- `benchmarks/tool_call_benchmark.py:61` — [benchmark_suite] ToolCall("file-06", "file", "Search for files matching *.py in the current directory.",
|
||||
- `benchmarks/tool_call_benchmark.py:63` — [benchmark_suite] ToolCall("file-07", "file", "Read the first 10 lines of /etc/passwd",
|
||||
- `benchmarks/tool_call_benchmark.py:65` — [benchmark_suite] ToolCall("file-08", "file", "Write a JSON config to /tmp/bench_config.json with key 'debug': true",
|
||||
- `benchmarks/tool_call_benchmark.py:67` — [benchmark_suite] ToolCall("file-09", "file", "Search for 'def test_' in Python test files.",
|
||||
- `benchmarks/tool_call_benchmark.py:69` — [benchmark_suite] ToolCall("file-10", "file", "Read /tmp/bench_config.json and tell me what's in it.",
|
||||
- `benchmarks/tool_call_benchmark.py:71` — [benchmark_suite] ToolCall("file-11", "file", "Create a file /tmp/bench_readme.md with one line: '# Benchmark'",
|
||||
- `benchmarks/tool_call_benchmark.py:73` — [benchmark_suite] ToolCall("file-12", "file", "Search for 'TODO' comments in all .py files.",
|
||||
- `benchmarks/tool_call_benchmark.py:75` — [benchmark_suite] ToolCall("file-13", "file", "Read /tmp/bench_readme.md",
|
||||
- `benchmarks/tool_call_benchmark.py:77` — [benchmark_suite] ToolCall("file-14", "file", "Patch /tmp/bench_readme.md: replace '# Benchmark' with '# Tool Benchmark'",
|
||||
- `benchmarks/tool_call_benchmark.py:78` — [benchmark_suite] "patch", "Tool Benchmark"),
|
||||
- `benchmarks/tool_call_benchmark.py:79` — [benchmark_suite] ToolCall("file-15", "file", "Write a Python one-liner to /tmp/bench_hello.py that prints hello.",
|
||||
- `benchmarks/tool_call_benchmark.py:81` — [benchmark_suite] ToolCall("file-16", "file", "Search for all .json files in /tmp/.",
|
||||
- `benchmarks/tool_call_benchmark.py:83` — [benchmark_suite] ToolCall("file-17", "file", "Read /tmp/bench_hello.py and verify it has print('hello').",
|
||||
- `benchmarks/tool_call_benchmark.py:85` — [benchmark_suite] ToolCall("file-18", "file", "Patch /tmp/bench_hello.py to print 'hello world' instead of 'hello'.",
|
||||
- `benchmarks/tool_call_benchmark.py:87` — [benchmark_suite] ToolCall("file-19", "file", "List files matching 'bench*' in /tmp/.",
|
||||
- `benchmarks/tool_call_benchmark.py:89` — [benchmark_suite] ToolCall("file-20", "file", "Read /tmp/test_bench.txt again and summarize its contents.",
|
||||
- `benchmarks/tool_call_benchmark.py:93` — [benchmark_suite] ToolCall("term-01", "terminal", "Run `echo hello world` in the terminal.",
|
||||
- `benchmarks/tool_call_benchmark.py:95` — [benchmark_suite] ToolCall("term-02", "terminal", "Run `date` to get the current date and time.",
|
||||
- `benchmarks/tool_call_benchmark.py:97` — [benchmark_suite] ToolCall("term-03", "terminal", "Run `uname -a` to get system information.",
|
||||
- `benchmarks/tool_call_benchmark.py:99` — [benchmark_suite] ToolCall("term-04", "terminal", "Run `pwd` to show the current directory.",
|
||||
- `benchmarks/tool_call_benchmark.py:101` — [benchmark_suite] ToolCall("term-05", "terminal", "Run `ls -la /tmp/ | head -20` to list temp files.",
|
||||
- `benchmarks/tool_call_benchmark.py:103` — [benchmark_suite] ToolCall("term-06", "terminal", "Run `whoami` to show the current user.",
|
||||
- `benchmarks/tool_call_benchmark.py:105` — [benchmark_suite] ToolCall("term-07", "terminal", "Run `df -h` to show disk usage.",
|
||||
- `benchmarks/tool_call_benchmark.py:107` — [benchmark_suite] ToolCall("term-08", "terminal", "Run `python3 --version` to check Python version.",
|
||||
- `benchmarks/tool_call_benchmark.py:109` — [benchmark_suite] ToolCall("term-09", "terminal", "Run `cat /etc/hostname` to get the hostname.",
|
||||
- `benchmarks/tool_call_benchmark.py:111` — [benchmark_suite] ToolCall("term-10", "terminal", "Run `uptime` to see system uptime.",
|
||||
- `benchmarks/tool_call_benchmark.py:113` — [benchmark_suite] ToolCall("term-11", "terminal", "Run `env | grep PATH` to show the PATH variable.",
|
||||
- `benchmarks/tool_call_benchmark.py:115` — [benchmark_suite] ToolCall("term-12", "terminal", "Run `wc -l /etc/passwd` to count lines.",
|
||||
- `benchmarks/tool_call_benchmark.py:117` — [benchmark_suite] ToolCall("term-13", "terminal", "Run `echo $SHELL` to show the current shell.",
|
||||
- `benchmarks/tool_call_benchmark.py:119` — [benchmark_suite] ToolCall("term-14", "terminal", "Run `free -h || vm_stat` to check memory usage.",
|
||||
- `benchmarks/tool_call_benchmark.py:121` — [benchmark_suite] ToolCall("term-15", "terminal", "Run `id` to show user and group IDs.",
|
||||
- `benchmarks/tool_call_benchmark.py:123` — [benchmark_suite] ToolCall("term-16", "terminal", "Run `hostname` to get the machine hostname.",
|
||||
- `benchmarks/tool_call_benchmark.py:125` — [benchmark_suite] ToolCall("term-17", "terminal", "Run `echo {1..5}` to test brace expansion.",
|
||||
- `benchmarks/tool_call_benchmark.py:127` — [benchmark_suite] ToolCall("term-18", "terminal", "Run `seq 1 5` to generate a number sequence.",
|
||||
- `benchmarks/tool_call_benchmark.py:129` — [benchmark_suite] ToolCall("term-19", "terminal", "Run `python3 -c 'print(2+2)'` to compute 2+2.",
|
||||
- `benchmarks/tool_call_benchmark.py:131` — [benchmark_suite] ToolCall("term-20", "terminal", "Run `ls -d /tmp/bench* 2>/dev/null | wc -l` to count bench files.",
|
||||
- `benchmarks/tool_call_benchmark.py:135` — [benchmark_suite] ToolCall("code-01", "code", "Execute a Python script that computes factorial of 10.",
|
||||
- `benchmarks/tool_call_benchmark.py:137` — [benchmark_suite] ToolCall("code-02", "code", "Run Python to read /tmp/test_bench.txt and count its words.",
|
||||
- `benchmarks/tool_call_benchmark.py:139` — [benchmark_suite] ToolCall("code-03", "code", "Execute Python to generate the first 20 Fibonacci numbers.",
|
||||
- `benchmarks/tool_call_benchmark.py:141` — [benchmark_suite] ToolCall("code-04", "code", "Run Python to parse JSON from a string and print keys.",
|
||||
- `benchmarks/tool_call_benchmark.py:143` — [benchmark_suite] ToolCall("code-05", "code", "Execute Python to list all files in /tmp/ matching 'bench*'.",
|
||||
- `benchmarks/tool_call_benchmark.py:145` — [benchmark_suite] ToolCall("code-06", "code", "Run Python to compute the sum of squares from 1 to 100.",
|
||||
- `benchmarks/tool_call_benchmark.py:147` — [benchmark_suite] ToolCall("code-07", "code", "Execute Python to check if 'racecar' is a palindrome.",
|
||||
- `benchmarks/tool_call_benchmark.py:149` — [benchmark_suite] ToolCall("code-08", "code", "Run Python to create a CSV string with 5 rows of sample data.",
|
||||
- `benchmarks/tool_call_benchmark.py:151` — [benchmark_suite] ToolCall("code-09", "code", "Execute Python to sort a list [5,2,8,1,9] and print the result.",
|
||||
- `benchmarks/tool_call_benchmark.py:153` — [benchmark_suite] ToolCall("code-10", "code", "Run Python to count lines in /etc/passwd.",
|
||||
- `benchmarks/tool_call_benchmark.py:155` — [benchmark_suite] ToolCall("code-11", "code", "Execute Python to hash the string 'benchmark' with SHA256.",
|
||||
- `benchmarks/tool_call_benchmark.py:157` — [benchmark_suite] ToolCall("code-12", "code", "Run Python to get the current UTC timestamp.",
|
||||
- `benchmarks/tool_call_benchmark.py:159` — [benchmark_suite] ToolCall("code-13", "code", "Execute Python to convert 'hello world' to uppercase and reverse it.",
|
||||
- `benchmarks/tool_call_benchmark.py:161` — [benchmark_suite] ToolCall("code-14", "code", "Run Python to create a dictionary of system info (platform, python version).",
|
||||
- `benchmarks/tool_call_benchmark.py:163` — [benchmark_suite] ToolCall("code-15", "code", "Execute Python to check internet connectivity by resolving google.com.",
|
||||
- `benchmarks/tool_call_benchmark.py:167` — [benchmark_suite] ToolCall("deleg-01", "delegate", "Use a subagent to find all .log files in /tmp/.",
|
||||
- `benchmarks/tool_call_benchmark.py:169` — [benchmark_suite] ToolCall("deleg-02", "delegate", "Delegate to a subagent: what is 15 * 37?",
|
||||
- `benchmarks/tool_call_benchmark.py:171` — [benchmark_suite] ToolCall("deleg-03", "delegate", "Use a subagent to check if Python 3 is installed and its version.",
|
||||
- `benchmarks/tool_call_benchmark.py:173` — [benchmark_suite] ToolCall("deleg-04", "delegate", "Delegate: read /tmp/test_bench.txt and summarize it in one sentence.",
|
||||
- `benchmarks/tool_call_benchmark.py:175` — [benchmark_suite] ToolCall("deleg-05", "delegate", "Use a subagent to list the contents of /tmp/ directory.",
|
||||
- `benchmarks/tool_call_benchmark.py:177` — [benchmark_suite] ToolCall("deleg-06", "delegate", "Delegate: count the number of .py files in the current directory.",
|
||||
- `benchmarks/tool_call_benchmark.py:179` — [benchmark_suite] ToolCall("deleg-07", "delegate", "Use a subagent to check disk space with df -h.",
|
||||
- `benchmarks/tool_call_benchmark.py:181` — [benchmark_suite] ToolCall("deleg-08", "delegate", "Delegate: what OS are we running on?",
|
||||
- `benchmarks/tool_call_benchmark.py:183` — [benchmark_suite] ToolCall("deleg-09", "delegate", "Use a subagent to find the hostname of this machine.",
|
||||
- `benchmarks/tool_call_benchmark.py:185` — [benchmark_suite] ToolCall("deleg-10", "delegate", "Delegate: create a temp file /tmp/bench_deleg.txt with 'done'.",
|
||||
- `benchmarks/tool_call_benchmark.py:189` — [benchmark_suite] ToolCall("todo-01", "todo", "Add a todo item: 'Run benchmark suite'",
|
||||
- `benchmarks/tool_call_benchmark.py:190` — [benchmark_suite] "todo", "benchmark"),
|
||||
- `benchmarks/tool_call_benchmark.py:191` — [benchmark_suite] ToolCall("todo-02", "todo", "Show me the current todo list.",
|
||||
- `benchmarks/tool_call_benchmark.py:193` — [benchmark_suite] ToolCall("todo-03", "todo", "Mark the first todo item as completed.",
|
||||
- `benchmarks/tool_call_benchmark.py:195` — [benchmark_suite] ToolCall("todo-04", "todo", "Add a todo: 'Review benchmark results' with status pending.",
|
||||
- `benchmarks/tool_call_benchmark.py:197` — [benchmark_suite] ToolCall("todo-05", "todo", "Clear all completed todos.",
|
||||
- `benchmarks/tool_call_benchmark.py:199` — [benchmark_suite] ToolCall("todo-06", "memory", "Save this to memory: 'benchmark ran on {date}'".format(
|
||||
- `benchmarks/tool_call_benchmark.py:201` — [benchmark_suite] "memory", "benchmark"),
|
||||
- `benchmarks/tool_call_benchmark.py:202` — [benchmark_suite] ToolCall("todo-07", "memory", "Search memory for 'benchmark'.",
|
||||
- `benchmarks/tool_call_benchmark.py:203` — [benchmark_suite] "memory", "benchmark"),
|
||||
- `benchmarks/tool_call_benchmark.py:204` — [benchmark_suite] ToolCall("todo-08", "memory", "Add a memory note: 'test models are gemma-4 and mimo-v2-pro'.",
|
||||
- `benchmarks/tool_call_benchmark.py:206` — [benchmark_suite] ToolCall("todo-09", "todo", "Add three todo items: 'analyze', 'report', 'cleanup'.",
|
||||
- `benchmarks/tool_call_benchmark.py:208` — [benchmark_suite] ToolCall("todo-10", "memory", "Search memory for any notes about models.",
|
||||
- `benchmarks/tool_call_benchmark.py:212` — [benchmark_suite] ToolCall("skill-01", "skills", "List all available skills.",
|
||||
- `benchmarks/tool_call_benchmark.py:214` — [benchmark_suite] ToolCall("skill-02", "skills", "View the skill called 'test-driven-development'.",
|
||||
- `benchmarks/tool_call_benchmark.py:216` — [benchmark_suite] ToolCall("skill-03", "skills", "Search for skills related to 'git'.",
|
||||
- `benchmarks/tool_call_benchmark.py:218` — [benchmark_suite] ToolCall("skill-04", "skills", "View the 'code-review' skill.",
|
||||
- `benchmarks/tool_call_benchmark.py:220` — [benchmark_suite] ToolCall("skill-05", "skills", "List all skills in the 'devops' category.",
|
||||
- `benchmarks/tool_call_benchmark.py:222` — [benchmark_suite] ToolCall("skill-06", "skills", "View the 'systematic-debugging' skill.",
|
||||
- `benchmarks/tool_call_benchmark.py:224` — [benchmark_suite] ToolCall("skill-07", "skills", "Search for skills about 'testing'.",
|
||||
- `benchmarks/tool_call_benchmark.py:226` — [benchmark_suite] ToolCall("skill-08", "skills", "View the 'writing-plans' skill.",
|
||||
- `benchmarks/tool_call_benchmark.py:228` — [benchmark_suite] ToolCall("skill-09", "skills", "List skills in 'software-development' category.",
|
||||
- `benchmarks/tool_call_benchmark.py:230` — [benchmark_suite] ToolCall("skill-10", "skills", "View the 'pr-review-discipline' skill.",
|
||||
- `benchmarks/tool_call_benchmark.py:234` — [benchmark_suite] ToolCall("file-21", "file", "Write a Python snippet to /tmp/bench_sort.py that sorts [3,1,2].",
|
||||
- `benchmarks/tool_call_benchmark.py:236` — [benchmark_suite] ToolCall("file-22", "file", "Read /tmp/bench_sort.py back and confirm it exists.",
|
||||
- `benchmarks/tool_call_benchmark.py:238` — [benchmark_suite] ToolCall("file-23", "file", "Search for 'class' in all .py files in the benchmarks directory.",
|
||||
- `benchmarks/tool_call_benchmark.py:240` — [benchmark_suite] ToolCall("term-21", "terminal", "Run `cat /etc/os-release 2>/dev/null || sw_vers 2>/dev/null` for OS info.",
|
||||
- `benchmarks/tool_call_benchmark.py:242` — [benchmark_suite] ToolCall("term-22", "terminal", "Run `nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null` for CPU count.",
|
||||
- `benchmarks/tool_call_benchmark.py:244` — [benchmark_suite] ToolCall("code-16", "code", "Execute Python to flatten a nested list [[1,2],[3,4],[5]].",
|
||||
- `benchmarks/tool_call_benchmark.py:246` — [benchmark_suite] ToolCall("code-17", "code", "Run Python to check if a number 17 is prime.",
|
||||
- `benchmarks/tool_call_benchmark.py:248` — [benchmark_suite] ToolCall("deleg-11", "delegate", "Delegate: what is the current working directory?",
|
||||
- `benchmarks/tool_call_benchmark.py:250` — [benchmark_suite] ToolCall("todo-11", "todo", "Add a todo: 'Finalize benchmark report' status pending.",
|
||||
- `benchmarks/tool_call_benchmark.py:252` — [benchmark_suite] ToolCall("todo-12", "memory", "Store fact: 'benchmark categories: file, terminal, code, delegate, todo, memory, skills'.",
|
||||
- `benchmarks/tool_call_benchmark.py:254` — [benchmark_suite] ToolCall("skill-11", "skills", "Search for skills about 'deployment'.",
|
||||
- `benchmarks/tool_call_benchmark.py:256` — [benchmark_suite] ToolCall("skill-12", "skills", "View the 'gitea-burn-cycle' skill.",
|
||||
- `benchmarks/tool_call_benchmark.py:258` — [benchmark_suite] ToolCall("skill-13", "skills", "List all available skill categories.",
|
||||
- `benchmarks/tool_call_benchmark.py:260` — [benchmark_suite] ToolCall("skill-14", "skills", "Search for skills related to 'memory'.",
|
||||
- `benchmarks/tool_call_benchmark.py:262` — [benchmark_suite] ToolCall("skill-15", "skills", "View the 'mimo-swarm' skill.",
|
||||
- `benchmarks/tool_call_benchmark.py:311` — [benchmark_suite] """Create prerequisite files for the benchmark."""
|
||||
- `benchmarks/tool_call_benchmark.py:313` — [benchmark_suite] "This is a benchmark test file.\n"
|
||||
- `benchmarks/tool_call_benchmark.py:349` — [benchmark_suite] "You are a benchmark test runner. Execute the user's request by calling "
|
||||
- `benchmarks/tool_call_benchmark.py:406` — [benchmark_suite] """Generate markdown benchmark report."""
|
||||
- `benchmarks/tool_call_benchmark.py:428` — [benchmark_suite] f"# Tool-Calling Benchmark Report",
|
||||
- `benchmarks/tool_call_benchmark.py:535` — [benchmark_suite] parser = argparse.ArgumentParser(description="Tool-calling benchmark")
|
||||
- `benchmarks/tool_call_benchmark.py:544` — [benchmark_suite] help="Output report path (default: benchmarks/gemma4-tool-calling-YYYY-MM-DD.md)")
|
||||
- `benchmarks/tool_call_benchmark.py:565` — [benchmark_suite] output_path = Path(args.output) if args.output else REPO_ROOT / "benchmarks" / f"gemma4-tool-calling-{date_str}.md"
|
||||
- `benchmarks/tool_call_benchmark.py:575` — [benchmark_suite] print(f"Benchmark: {len(suite)} tests × {len(model_specs)} models = {len(suite) * len(model_specs)} calls")
|
||||
|
||||
## Suggested next slice
|
||||
|
||||
1. Build an exporter that emits SessionDB + trajectory data into a TensorZero-friendly offline dataset.
|
||||
2. Define percentage-based canary controls before attempting any gateway replacement.
|
||||
3. Keep Hermes routing authoritative until TensorZero proves parity across CLI, gateway, cron, auxiliary, and delegation surfaces.
|
||||
67
metrics/vision-benchmark-smoke-2026-04-22.json
Normal file
67
metrics/vision-benchmark-smoke-2026-04-22.json
Normal file
@@ -0,0 +1,67 @@
|
||||
{
|
||||
"generated_at": "2026-04-22T16:21:56.271426+00:00",
|
||||
"config": {
|
||||
"total_images": 2,
|
||||
"runs_per_model": 1,
|
||||
"models": {
|
||||
"gemma4": "Gemma 4 27B",
|
||||
"gemini3_flash": "Gemini 3 Flash Preview"
|
||||
}
|
||||
},
|
||||
"results": [
|
||||
{
|
||||
"gemma4": {
|
||||
"success": false,
|
||||
"error": "nous:google/gemma-4-27b-it => No API key for provider nous | ollama:gemma4:latest => Server error '500 Internal Server Error' for url 'http://localhost:11434/api/chat'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/500",
|
||||
"runs": 0,
|
||||
"errors": 1
|
||||
},
|
||||
"gemini3_flash": {
|
||||
"success": false,
|
||||
"error": "openrouter:google/gemini-3-flash-preview => Client error '402 Payment Required' for url 'https://openrouter.ai/api/v1/chat/completions'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/402 | gemini:gemini-2.5-flash => Client error '429 Too Many Requests' for url 'https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent?key=AIzaSyAmIctJQG_b4VKV1sMLebBnouq6yCckEf0'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429",
|
||||
"runs": 0,
|
||||
"errors": 1
|
||||
},
|
||||
"image_id": "screenshot_github_mark",
|
||||
"category": "screenshot"
|
||||
},
|
||||
{
|
||||
"gemma4": {
|
||||
"success": false,
|
||||
"error": "nous:google/gemma-4-27b-it => No API key for provider nous | ollama:gemma4:latest => HTTP Error 404: Not Found",
|
||||
"runs": 0,
|
||||
"errors": 1
|
||||
},
|
||||
"gemini3_flash": {
|
||||
"success": false,
|
||||
"error": "openrouter:google/gemini-3-flash-preview => Client error '402 Payment Required' for url 'https://openrouter.ai/api/v1/chat/completions'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/402 | gemini:gemini-2.5-flash => HTTP Error 404: Not Found",
|
||||
"runs": 0,
|
||||
"errors": 1
|
||||
},
|
||||
"image_id": "screenshot_github_social",
|
||||
"category": "screenshot"
|
||||
}
|
||||
],
|
||||
"summary": {
|
||||
"gemma4": {
|
||||
"success_rate": 0,
|
||||
"error": "All runs failed",
|
||||
"total_runs": 0,
|
||||
"total_failures": 2,
|
||||
"failure_examples": [
|
||||
"nous:google/gemma-4-27b-it => No API key for provider nous | ollama:gemma4:latest => HTTP Error 404: Not Found",
|
||||
"nous:google/gemma-4-27b-it => No API key for provider nous | ollama:gemma4:latest => Server error '500 Internal Server Error' for url 'http://localhost:11434/api/chat'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/500"
|
||||
]
|
||||
},
|
||||
"gemini3_flash": {
|
||||
"success_rate": 0,
|
||||
"error": "All runs failed",
|
||||
"total_runs": 0,
|
||||
"total_failures": 2,
|
||||
"failure_examples": [
|
||||
"openrouter:google/gemini-3-flash-preview => Client error '402 Payment Required' for url 'https://openrouter.ai/api/v1/chat/completions'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/402 | gemini:gemini-2.5-flash => Client error '429 Too Many Requests' for url 'https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent?key=AIzaSyAmIctJQG_b4VKV1sMLebBnouq6yCckEf0'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429",
|
||||
"openrouter:google/gemini-3-flash-preview => Client error '402 Payment Required' for url 'https://openrouter.ai/api/v1/chat/completions'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/402 | gemini:gemini-2.5-flash => HTTP Error 404: Not Found"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
44
metrics/vision-benchmark-smoke-2026-04-22.md
Normal file
44
metrics/vision-benchmark-smoke-2026-04-22.md
Normal file
@@ -0,0 +1,44 @@
|
||||
# Vision Benchmark Report
|
||||
|
||||
Generated: 2026-04-22T16:21
|
||||
Images tested: 2
|
||||
Runs per model: 1
|
||||
Models: Gemma 4 27B, Gemini 3 Flash Preview
|
||||
|
||||
## Latency Comparison
|
||||
|
||||
| Model | Mean (ms) | Median | P95 | Std Dev |
|
||||
|-------|-----------|--------|-----|---------|
|
||||
|
||||
## Accuracy Comparison
|
||||
|
||||
| Model | OCR Accuracy | Keyword Coverage | Success Rate |
|
||||
|-------|-------------|-----------------|--------------|
|
||||
|
||||
## Token Usage
|
||||
|
||||
| Model | Mean Tokens/Image | Total Tokens |
|
||||
|-------|------------------|--------------|
|
||||
|
||||
## Failure Modes
|
||||
|
||||
### Gemma 4 27B
|
||||
- Summary: All runs failed
|
||||
- nous:google/gemma-4-27b-it => No API key for provider nous | ollama:gemma4:latest => HTTP Error 404: Not Found
|
||||
- nous:google/gemma-4-27b-it => No API key for provider nous | ollama:gemma4:latest => Server error '500 Internal Server Error' for url 'http://localhost:11434/api/chat'
|
||||
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/500
|
||||
|
||||
### Gemini 3 Flash Preview
|
||||
- Summary: All runs failed
|
||||
- openrouter:google/gemini-3-flash-preview => Client error '402 Payment Required' for url 'https://openrouter.ai/api/v1/chat/completions'
|
||||
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/402 | gemini:gemini-2.5-flash => Client error '429 Too Many Requests' for url 'https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent?key=AIzaSyAmIctJQG_b4VKV1sMLebBnouq6yCckEf0'
|
||||
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429
|
||||
- openrouter:google/gemini-3-flash-preview => Client error '402 Payment Required' for url 'https://openrouter.ai/api/v1/chat/completions'
|
||||
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/402 | gemini:gemini-2.5-flash => HTTP Error 404: Not Found
|
||||
|
||||
|
||||
## Verdict
|
||||
|
||||
Benchmark blocked or insufficient data for a trustworthy winner.
|
||||
|
||||
Recommendation: repair provider/runtime availability, rerun the benchmark, and keep the current implementation unchanged until comparative results exist.
|
||||
@@ -1,318 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Generate a grounded TensorZero evaluation packet for Hermes.
|
||||
|
||||
This script inventories the current Hermes routing/evaluation surfaces, then
|
||||
builds a markdown packet assessing how much of issue #860 can be satisfied by
|
||||
TensorZero and where the migration risk still lives.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import re
|
||||
from dataclasses import asdict, dataclass
|
||||
from pathlib import Path
|
||||
from typing import Iterable
|
||||
|
||||
ISSUE_NUMBER = 860
|
||||
ISSUE_TITLE = "tensorzero LLMOps platform evaluation"
|
||||
ISSUE_URL = "https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/860"
|
||||
DEFAULT_OUTPUT = Path("docs/evaluations/tensorzero-860-evaluation.md")
|
||||
DEFAULT_JSON_OUTPUT = Path("docs/evaluations/tensorzero-860-evaluation.json")
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TouchpointPattern:
|
||||
label: str
|
||||
file_path: str
|
||||
regex: str
|
||||
description: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class Touchpoint:
|
||||
label: str
|
||||
file_path: str
|
||||
line_number: int
|
||||
matched_text: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RequirementStatus:
|
||||
key: str
|
||||
name: str
|
||||
status: str
|
||||
evidence_labels: tuple[str, ...]
|
||||
summary: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class EvaluationReport:
|
||||
issue_number: int
|
||||
issue_title: str
|
||||
issue_url: str
|
||||
recommendation: str
|
||||
touchpoints: tuple[Touchpoint, ...]
|
||||
requirements: tuple[RequirementStatus, ...]
|
||||
|
||||
|
||||
PATTERNS: tuple[TouchpointPattern, ...] = (
|
||||
TouchpointPattern(
|
||||
label="fallback_chain",
|
||||
file_path="run_agent.py",
|
||||
regex=r"_fallback_chain|fallback_providers|fallback_model",
|
||||
description="Primary agent fallback-provider chain in the core conversation loop.",
|
||||
),
|
||||
TouchpointPattern(
|
||||
label="provider_routing_config",
|
||||
file_path="cli.py",
|
||||
regex=r"provider_routing|fallback_providers|smart_model_routing",
|
||||
description="CLI-owned provider routing and fallback configuration surfaces.",
|
||||
),
|
||||
TouchpointPattern(
|
||||
label="runtime_provider",
|
||||
file_path="hermes_cli/runtime_provider.py",
|
||||
regex=r"def resolve_runtime_provider|def resolve_requested_provider",
|
||||
description="Central runtime provider resolution for CLI, gateway, cron, and helpers.",
|
||||
),
|
||||
TouchpointPattern(
|
||||
label="smart_model_routing",
|
||||
file_path="agent/smart_model_routing.py",
|
||||
regex=r"def resolve_turn_route|def choose_cheap_model_route",
|
||||
description="Cheap-vs-strong turn routing that TensorZero would need to absorb or replace.",
|
||||
),
|
||||
TouchpointPattern(
|
||||
label="gateway_provider_routing",
|
||||
file_path="gateway/run.py",
|
||||
regex=r"def _load_provider_routing|def _load_fallback_model|def _load_smart_model_routing",
|
||||
description="Gateway-specific loading of routing, fallback, and smart-model policies.",
|
||||
),
|
||||
TouchpointPattern(
|
||||
label="cron_runtime_provider",
|
||||
file_path="cron/scheduler.py",
|
||||
regex=r"resolve_runtime_provider|resolve_turn_route|provider_routing|fallback_model",
|
||||
description="Cron execution path that re-resolves providers and routing on every run.",
|
||||
),
|
||||
TouchpointPattern(
|
||||
label="auxiliary_fallback_chain",
|
||||
file_path="agent/auxiliary_client.py",
|
||||
regex=r"fallback chain|_get_provider_chain|provider chain",
|
||||
description="Auxiliary task routing/fallback chain outside the main inference path.",
|
||||
),
|
||||
TouchpointPattern(
|
||||
label="delegate_runtime_provider",
|
||||
file_path="tools/delegate_tool.py",
|
||||
regex=r"runtime provider system|resolve the full credential bundle|resolve_runtime_provider",
|
||||
description="Subagent/delegation routing path that would also need TensorZero parity.",
|
||||
),
|
||||
TouchpointPattern(
|
||||
label="session_db",
|
||||
file_path="hermes_state.py",
|
||||
regex=r"class SessionDB",
|
||||
description="Session persistence surface that could feed TensorZero optimization/eval data.",
|
||||
),
|
||||
TouchpointPattern(
|
||||
label="trajectory_export",
|
||||
file_path="batch_runner.py",
|
||||
regex=r"trajectory_entry|save_trajectories|_convert_to_trajectory_format",
|
||||
description="Trajectory export surface for offline optimization and replay data.",
|
||||
),
|
||||
TouchpointPattern(
|
||||
label="benchmark_suite",
|
||||
file_path="benchmarks/tool_call_benchmark.py",
|
||||
regex=r"ToolCall\(|class ToolCall|benchmark",
|
||||
description="Existing benchmark/evaluation harness that could map to TensorZero experiments.",
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def _iter_matches(pattern: TouchpointPattern, text: str) -> Iterable[Touchpoint]:
|
||||
regex = re.compile(pattern.regex, re.IGNORECASE)
|
||||
for line_number, line in enumerate(text.splitlines(), start=1):
|
||||
if regex.search(line):
|
||||
yield Touchpoint(
|
||||
label=pattern.label,
|
||||
file_path=pattern.file_path,
|
||||
line_number=line_number,
|
||||
matched_text=line.strip(),
|
||||
)
|
||||
|
||||
|
||||
def scan_touchpoints(repo_root: Path) -> list[Touchpoint]:
|
||||
touchpoints: list[Touchpoint] = []
|
||||
for pattern in PATTERNS:
|
||||
path = repo_root / pattern.file_path
|
||||
if not path.exists():
|
||||
continue
|
||||
text = path.read_text(encoding="utf-8")
|
||||
touchpoints.extend(_iter_matches(pattern, text))
|
||||
return touchpoints
|
||||
|
||||
|
||||
def build_requirement_matrix(touchpoints: list[Touchpoint]) -> list[RequirementStatus]:
|
||||
labels = {tp.label for tp in touchpoints}
|
||||
|
||||
matrix: list[RequirementStatus] = []
|
||||
gateway_labels = (
|
||||
"fallback_chain",
|
||||
"runtime_provider",
|
||||
"gateway_provider_routing",
|
||||
"cron_runtime_provider",
|
||||
"auxiliary_fallback_chain",
|
||||
"delegate_runtime_provider",
|
||||
)
|
||||
gateway_hits = tuple(label for label in gateway_labels if label in labels)
|
||||
gateway_status = "partial" if len(gateway_hits) >= 4 else "gap"
|
||||
gateway_summary = (
|
||||
"Hermes already spreads provider routing across core agent, runtime provider, gateway, cron, auxiliary, and delegation seams; "
|
||||
"TensorZero would need parity across all of them before it can replace the gateway layer."
|
||||
if gateway_hits else
|
||||
"No grounded routing surfaces were found for a gateway replacement assessment."
|
||||
)
|
||||
matrix.append(RequirementStatus("gateway_replacement", "Gateway replacement scope", gateway_status, gateway_hits, gateway_summary))
|
||||
|
||||
config_labels = (
|
||||
"provider_routing_config",
|
||||
"runtime_provider",
|
||||
"smart_model_routing",
|
||||
"fallback_chain",
|
||||
)
|
||||
config_hits = tuple(label for label in config_labels if label in labels)
|
||||
config_status = "partial" if len(config_hits) >= 3 else "gap"
|
||||
config_summary = (
|
||||
"Hermes has multiple config concepts to migrate (`provider_routing`, `fallback_providers`, `smart_model_routing`, runtime provider resolution), "
|
||||
"so TensorZero is not a drop-in config swap."
|
||||
if config_hits else
|
||||
"No current config migration surface was found."
|
||||
)
|
||||
matrix.append(RequirementStatus("config_migration", "Config migration", config_status, config_hits, config_summary))
|
||||
|
||||
canary_hits: tuple[str, ...] = tuple()
|
||||
canary_summary = (
|
||||
"The repo shows semantic routing and fallback, but no grounded 10% traffic-split canary mechanism. "
|
||||
"A TensorZero cutover would need new percentage-based rollout controls and observability hooks."
|
||||
)
|
||||
matrix.append(RequirementStatus("canary_rollout", "10% traffic canary", "gap", canary_hits, canary_summary))
|
||||
|
||||
session_labels = ("session_db", "trajectory_export")
|
||||
session_hits = tuple(label for label in session_labels if label in labels)
|
||||
session_status = "partial" if len(session_hits) == len(session_labels) else "gap"
|
||||
session_summary = (
|
||||
"Hermes already has SessionDB and trajectory export surfaces that can feed offline optimization data, "
|
||||
"but not a TensorZero-native ingestion path yet."
|
||||
if session_hits else
|
||||
"No session-data surface was found for prompt optimization."
|
||||
)
|
||||
matrix.append(RequirementStatus("session_feedback", "Session data for prompt optimization", session_status, session_hits, session_summary))
|
||||
|
||||
eval_labels = ("benchmark_suite", "trajectory_export")
|
||||
eval_hits = tuple(label for label in eval_labels if label in labels)
|
||||
eval_status = "partial" if "benchmark_suite" in eval_hits else "gap"
|
||||
eval_summary = (
|
||||
"Hermes already has benchmark/trajectory machinery that can seed TensorZero A/B evaluation, "
|
||||
"but no integrated TensorZero experiment runner or live evaluation gateway."
|
||||
if eval_hits else
|
||||
"No evaluation harness was found to support TensorZero A/B testing."
|
||||
)
|
||||
matrix.append(RequirementStatus("evaluation_suite", "Evaluation suite / A/B testing", eval_status, eval_hits, eval_summary))
|
||||
|
||||
return matrix
|
||||
|
||||
|
||||
def build_report(touchpoints: list[Touchpoint], requirement_matrix: list[RequirementStatus]) -> EvaluationReport:
|
||||
recommendation = (
|
||||
"Not ready for direct replacement. Recommend a shadow-evaluation phase first: keep Hermes routing live, "
|
||||
"inventory the migration seams, export SessionDB/trajectory data into an offline TensorZero experiment loop, "
|
||||
"and only design a canary gateway once percentage-based rollout controls exist."
|
||||
)
|
||||
return EvaluationReport(
|
||||
issue_number=ISSUE_NUMBER,
|
||||
issue_title=ISSUE_TITLE,
|
||||
issue_url=ISSUE_URL,
|
||||
recommendation=recommendation,
|
||||
touchpoints=tuple(touchpoints),
|
||||
requirements=tuple(requirement_matrix),
|
||||
)
|
||||
|
||||
|
||||
def build_markdown(report: EvaluationReport) -> str:
|
||||
lines: list[str] = []
|
||||
lines.append("# TensorZero Evaluation Packet")
|
||||
lines.append("")
|
||||
lines.append(f"Issue #{report.issue_number}: [{report.issue_title}]({report.issue_url})")
|
||||
lines.append("")
|
||||
lines.append("## Scope")
|
||||
lines.append("")
|
||||
lines.append("This packet evaluates TensorZero as a possible replacement for Hermes' custom provider-routing stack.")
|
||||
lines.append("It is intentionally grounded in the current repo state rather than a speculative cutover plan.")
|
||||
lines.append("")
|
||||
lines.append("## Issue requirements being evaluated")
|
||||
lines.append("")
|
||||
lines.append("- Deploy tensorzero gateway (Rust binary)")
|
||||
lines.append("- Migrate provider routing config")
|
||||
lines.append("- Test with canary (10% traffic) before full cutover")
|
||||
lines.append("- Feed session data for prompt optimization")
|
||||
lines.append("- Evaluation suite for A/B testing models")
|
||||
lines.append("")
|
||||
lines.append("## Recommendation")
|
||||
lines.append("")
|
||||
lines.append(report.recommendation)
|
||||
lines.append("")
|
||||
lines.append("## Requirement matrix")
|
||||
lines.append("")
|
||||
lines.append("| Requirement | Status | Evidence labels | Summary |")
|
||||
lines.append("| --- | --- | --- | --- |")
|
||||
for row in report.requirements:
|
||||
evidence = ", ".join(row.evidence_labels) if row.evidence_labels else "—"
|
||||
lines.append(f"| {row.name} | {row.status} | {evidence} | {row.summary} |")
|
||||
lines.append("")
|
||||
lines.append("## Grounded Hermes touchpoints")
|
||||
lines.append("")
|
||||
if report.touchpoints:
|
||||
for tp in report.touchpoints:
|
||||
lines.append(f"- `{tp.file_path}:{tp.line_number}` — [{tp.label}] {tp.matched_text}")
|
||||
else:
|
||||
lines.append("- No routing/evaluation touchpoints were found.")
|
||||
lines.append("")
|
||||
lines.append("## Suggested next slice")
|
||||
lines.append("")
|
||||
lines.append("1. Build an exporter that emits SessionDB + trajectory data into a TensorZero-friendly offline dataset.")
|
||||
lines.append("2. Define percentage-based canary controls before attempting any gateway replacement.")
|
||||
lines.append("3. Keep Hermes routing authoritative until TensorZero proves parity across CLI, gateway, cron, auxiliary, and delegation surfaces.")
|
||||
lines.append("")
|
||||
return "\n".join(lines).rstrip() + "\n"
|
||||
|
||||
|
||||
def write_outputs(report: EvaluationReport, markdown_path: Path, json_path: Path | None = None) -> None:
|
||||
markdown_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
markdown_path.write_text(build_markdown(report), encoding="utf-8")
|
||||
if json_path is not None:
|
||||
json_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
json_path.write_text(json.dumps(asdict(report), indent=2), encoding="utf-8")
|
||||
|
||||
|
||||
def parse_args() -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(description="Generate a grounded TensorZero evaluation packet for Hermes")
|
||||
parser.add_argument("--repo-root", default=".", help="Hermes repo root to scan")
|
||||
parser.add_argument("--output", default=str(DEFAULT_OUTPUT), help="Markdown output path")
|
||||
parser.add_argument("--json-output", default=str(DEFAULT_JSON_OUTPUT), help="Optional JSON output path")
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def main() -> int:
|
||||
args = parse_args()
|
||||
repo_root = Path(args.repo_root).resolve()
|
||||
touchpoints = scan_touchpoints(repo_root)
|
||||
matrix = build_requirement_matrix(touchpoints)
|
||||
report = build_report(touchpoints, matrix)
|
||||
json_output = Path(args.json_output) if args.json_output else None
|
||||
write_outputs(report, Path(args.output), json_output)
|
||||
print(f"Wrote {args.output}")
|
||||
if json_output is not None:
|
||||
print(f"Wrote {json_output}")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -1,149 +0,0 @@
|
||||
from pathlib import Path
|
||||
import sys
|
||||
|
||||
SCRIPT_DIR = Path(__file__).resolve().parents[1] / "scripts"
|
||||
sys.path.insert(0, str(SCRIPT_DIR))
|
||||
|
||||
import tensorzero_eval_packet as tz
|
||||
|
||||
|
||||
def test_scan_touchpoints_finds_expected_matches(tmp_path):
|
||||
(tmp_path / "run_agent.py").write_text(
|
||||
"self._fallback_chain = []\n# Provider fallback chain\n"
|
||||
)
|
||||
(tmp_path / "hermes_cli").mkdir()
|
||||
(tmp_path / "hermes_cli" / "runtime_provider.py").write_text(
|
||||
"def resolve_runtime_provider():\n return {}\n"
|
||||
)
|
||||
(tmp_path / "agent").mkdir()
|
||||
(tmp_path / "agent" / "smart_model_routing.py").write_text(
|
||||
"def resolve_turn_route(user_message, routing_config, primary):\n return primary\n"
|
||||
)
|
||||
(tmp_path / "gateway").mkdir()
|
||||
(tmp_path / "gateway" / "run.py").write_text(
|
||||
"def _load_provider_routing():\n return {}\n"
|
||||
)
|
||||
(tmp_path / "cron").mkdir()
|
||||
(tmp_path / "cron" / "scheduler.py").write_text(
|
||||
"runtime = resolve_runtime_provider()\nturn_route = resolve_turn_route('x', {}, {})\n"
|
||||
)
|
||||
(tmp_path / "hermes_state.py").write_text("class SessionDB:\n pass\n")
|
||||
(tmp_path / "benchmarks").mkdir()
|
||||
(tmp_path / "benchmarks" / "tool_call_benchmark.py").write_text(
|
||||
"class ToolCall: ...\n"
|
||||
)
|
||||
|
||||
touchpoints = tz.scan_touchpoints(tmp_path)
|
||||
|
||||
labels = {tp.label for tp in touchpoints}
|
||||
assert "fallback_chain" in labels
|
||||
assert "runtime_provider" in labels
|
||||
assert "smart_model_routing" in labels
|
||||
assert "gateway_provider_routing" in labels
|
||||
assert "cron_runtime_provider" in labels
|
||||
assert "session_db" in labels
|
||||
assert "benchmark_suite" in labels
|
||||
|
||||
|
||||
def test_build_requirement_matrix_marks_canary_as_gap_without_split_support():
|
||||
touchpoints = [
|
||||
tz.Touchpoint(
|
||||
label="runtime_provider",
|
||||
file_path="hermes_cli/runtime_provider.py",
|
||||
line_number=10,
|
||||
matched_text="def resolve_runtime_provider",
|
||||
),
|
||||
tz.Touchpoint(
|
||||
label="provider_routing_config",
|
||||
file_path="cli.py",
|
||||
line_number=20,
|
||||
matched_text='provider_routing',
|
||||
),
|
||||
tz.Touchpoint(
|
||||
label="fallback_chain",
|
||||
file_path="run_agent.py",
|
||||
line_number=21,
|
||||
matched_text='_fallback_chain = []',
|
||||
),
|
||||
tz.Touchpoint(
|
||||
label="smart_model_routing",
|
||||
file_path="agent/smart_model_routing.py",
|
||||
line_number=30,
|
||||
matched_text='resolve_turn_route',
|
||||
),
|
||||
tz.Touchpoint(
|
||||
label="gateway_provider_routing",
|
||||
file_path="gateway/run.py",
|
||||
line_number=35,
|
||||
matched_text='def _load_provider_routing',
|
||||
),
|
||||
tz.Touchpoint(
|
||||
label="cron_runtime_provider",
|
||||
file_path="cron/scheduler.py",
|
||||
line_number=36,
|
||||
matched_text='runtime = resolve_runtime_provider()',
|
||||
),
|
||||
tz.Touchpoint(
|
||||
label="session_db",
|
||||
file_path="hermes_state.py",
|
||||
line_number=40,
|
||||
matched_text='class SessionDB',
|
||||
),
|
||||
tz.Touchpoint(
|
||||
label="trajectory_export",
|
||||
file_path="batch_runner.py",
|
||||
line_number=50,
|
||||
matched_text='trajectory_entry',
|
||||
),
|
||||
tz.Touchpoint(
|
||||
label="benchmark_suite",
|
||||
file_path="benchmarks/tool_call_benchmark.py",
|
||||
line_number=60,
|
||||
matched_text='ToolCall',
|
||||
),
|
||||
]
|
||||
|
||||
matrix = tz.build_requirement_matrix(touchpoints)
|
||||
by_key = {row.key: row for row in matrix}
|
||||
|
||||
assert by_key["gateway_replacement"].status == "partial"
|
||||
assert by_key["config_migration"].status == "partial"
|
||||
assert by_key["canary_rollout"].status == "gap"
|
||||
assert by_key["session_feedback"].status == "partial"
|
||||
assert by_key["evaluation_suite"].status == "partial"
|
||||
|
||||
|
||||
def test_build_markdown_renders_recommendation_and_touchpoints():
|
||||
touchpoints = [
|
||||
tz.Touchpoint(
|
||||
label="runtime_provider",
|
||||
file_path="hermes_cli/runtime_provider.py",
|
||||
line_number=10,
|
||||
matched_text="def resolve_runtime_provider",
|
||||
),
|
||||
tz.Touchpoint(
|
||||
label="session_db",
|
||||
file_path="hermes_state.py",
|
||||
line_number=40,
|
||||
matched_text='class SessionDB',
|
||||
),
|
||||
]
|
||||
matrix = tz.build_requirement_matrix(touchpoints)
|
||||
report = tz.build_report(touchpoints, matrix)
|
||||
markdown = tz.build_markdown(report)
|
||||
|
||||
assert "# TensorZero Evaluation Packet" in markdown
|
||||
assert "gateway_replacement" not in markdown # human labels, not raw keys
|
||||
assert "Gateway replacement scope" in markdown
|
||||
assert "Not ready for direct replacement" in markdown
|
||||
assert "hermes_cli/runtime_provider.py:10" in markdown
|
||||
assert "hermes_state.py:40" in markdown
|
||||
|
||||
|
||||
def test_issue_context_is_embedded_in_report():
|
||||
report = tz.build_report([], [])
|
||||
markdown = tz.build_markdown(report)
|
||||
|
||||
assert "Issue #860" in markdown
|
||||
assert "tensorzero" in markdown.lower()
|
||||
assert "10% traffic" in markdown
|
||||
@@ -199,7 +199,7 @@ class TestMarkdown:
|
||||
class TestDataset:
|
||||
def test_sample_dataset_has_entries(self):
|
||||
dataset = generate_sample_dataset()
|
||||
assert len(dataset) >= 4
|
||||
assert len(dataset) >= 50
|
||||
|
||||
def test_sample_dataset_structure(self):
|
||||
dataset = generate_sample_dataset()
|
||||
@@ -216,6 +216,9 @@ class TestDataset:
|
||||
assert "screenshot" in categories
|
||||
assert "diagram" in categories
|
||||
assert "photo" in categories
|
||||
assert "chart" in categories
|
||||
assert "ocr" in categories
|
||||
assert "document" in categories
|
||||
|
||||
|
||||
class TestModels:
|
||||
|
||||
21
tests/test_vision_benchmark_artifacts.py
Normal file
21
tests/test_vision_benchmark_artifacts.py
Normal file
@@ -0,0 +1,21 @@
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
DATASET = Path("benchmarks/test_images.json")
|
||||
REPORT = Path("metrics/vision-benchmark-smoke-2026-04-22.md")
|
||||
|
||||
|
||||
def test_benchmark_dataset_is_issue_sized_and_category_complete() -> None:
|
||||
items = json.loads(DATASET.read_text(encoding="utf-8"))
|
||||
assert len(items) >= 50
|
||||
categories = {item["category"] for item in items}
|
||||
assert {"screenshot", "diagram", "photo", "ocr", "chart", "document"}.issubset(categories)
|
||||
|
||||
|
||||
def test_metrics_report_exists_with_recommendation() -> None:
|
||||
assert REPORT.exists(), "missing benchmark report under metrics/"
|
||||
text = REPORT.read_text(encoding="utf-8")
|
||||
assert "Recommendation" in text
|
||||
assert "Gemma 4" in text
|
||||
assert "Gemini" in text
|
||||
Reference in New Issue
Block a user